< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 362 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.5134. Min Act: -0.1700

Data Index: 1106503 (Open Web Text)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.4741. Min Act: -0.1700

Data Index: 8386047 (Open Web Text)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.4764. Min Act: -0.1700

Data Index: 7379320 (Open Web Text)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.4389. Min Act: -0.1700

Data Index: 4894011 (Open Web Text)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.4240. Min Act: -0.1700

Data Index: 7399741 (Open Web Text)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.4123. Min Act: -0.1700

Data Index: 8251316 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.3875. Min Act: -0.1700

Data Index: 411794 (Open Web Text)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.4310. Min Act: -0.1700

Data Index: 7674551 (Open Web Text)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.4154. Min Act: -0.1700

Data Index: 3500068 (Open Web Text)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.3642. Min Act: -0.1700

Data Index: 3783666 (Open Web Text)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.3457. Min Act: -0.1700

Data Index: 3256900 (Open Web Text)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.3173. Min Act: -0.1700

Data Index: 1994163 (Open Web Text)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.2868. Min Act: -0.1700

Data Index: 7423576 (Open Web Text)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.2893. Min Act: -0.1700

Data Index: 5284853 (Open Web Text)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.3193. Min Act: -0.1700

Data Index: 6307832 (Open Web Text)

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.2362. Min Act: -0.1700

Data Index: 2014849 (Open Web Text)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.2566. Min Act: -0.1700

Data Index: 5843672 (Open Web Text)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.2406. Min Act: -0.1700

Data Index: 1420120 (Open Web Text)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.2475. Min Act: -0.1700

Data Index: 4991071 (Open Web Text)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.5134. Min Range: -2.5134

Max Act: 2.2625. Min Act: -0.1700

Data Index: 8254097 (Open Web Text)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #19