< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1199 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.5888. Min Act: -0.1700

Data Index: 7416472 (Open Web Text)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.5144. Min Act: -0.1700

Data Index: 89427 (Open Web Text)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.5167. Min Act: -0.1700

Data Index: 5477060 (Open Web Text)

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.5068. Min Act: -0.1700

Data Index: 6972998 (Open Web Text)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.4703. Min Act: -0.1700

Data Index: 1545467 (Open Web Text)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.4450. Min Act: -0.1700

Data Index: 7961919 (Open Web Text)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.4333. Min Act: -0.1700

Data Index: 6945042 (Open Web Text)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.4055. Min Act: -0.1700

Data Index: 2145190 (Open Web Text)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.4172. Min Act: -0.1700

Data Index: 5120888 (Open Web Text)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.4031. Min Act: -0.1700

Data Index: 8172859 (Open Web Text)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.4057. Min Act: -0.1700

Data Index: 563561 (Open Web Text)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.3712. Min Act: -0.1700

Data Index: 1323598 (Open Web Text)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.3465. Min Act: -0.1700

Data Index: 6064281 (Open Web Text)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.3535. Min Act: -0.1700

Data Index: 2222751 (Open Web Text)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.3499. Min Act: -0.1700

Data Index: 4094121 (Open Web Text)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.3445. Min Act: -0.1700

Data Index: 2087144 (Open Web Text)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.3460. Min Act: -0.1700

Data Index: 2482480 (Open Web Text)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.3016. Min Act: -0.1700

Data Index: 5960945 (Open Web Text)

Max Activating Token Index: 726

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.3142. Min Act: -0.1700

Data Index: 3001346 (Open Web Text)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.5888. Min Range: -4.5888

Max Act: 4.3229. Min Act: -0.1700

Data Index: 8184863 (Open Web Text)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #19