< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1726 in Layer 1

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: 2.1163. Min Range: -2.1163

Max Act: 2.1163. Min Act: -0.1700

Data Index: 7462738 (Open Web Text)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0974. Min Act: -0.1700

Data Index: 923441 (Open Web Text)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.1058. Min Act: -0.1700

Data Index: 5967143 (Open Web Text)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0601. Min Act: -0.1700

Data Index: 6735966 (Open Web Text)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0761. Min Act: -0.1700

Data Index: 4207800 (Open Web Text)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0702. Min Act: -0.1700

Data Index: 6568740 (Open Web Text)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0641. Min Act: -0.1700

Data Index: 7798192 (Open Web Text)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0490. Min Act: -0.1699

Data Index: 7127445 (Open Web Text)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0315. Min Act: -0.1700

Data Index: 6096570 (Open Web Text)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0353. Min Act: -0.1700

Data Index: 1427330 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0434. Min Act: -0.1700

Data Index: 5498798 (Open Web Text)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0317. Min Act: -0.1700

Data Index: 8443166 (Open Web Text)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0277. Min Act: -0.1700

Data Index: 1604184 (Open Web Text)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0455. Min Act: -0.1700

Data Index: 8192172 (Open Web Text)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0294. Min Act: -0.1700

Data Index: 4368724 (Open Web Text)

Max Activating Token Index: 409

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0364. Min Act: -0.1700

Data Index: 2222232 (Open Web Text)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0285. Min Act: -0.1700

Data Index: 6723886 (Open Web Text)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0406. Min Act: -0.1700

Data Index: 1782944 (Open Web Text)

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0109. Min Act: -0.1700

Data Index: 5517543 (Open Web Text)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1163. Min Range: -2.1163

Max Act: 2.0123. Min Act: -0.1700

Data Index: 5893595 (Open Web Text)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #19