< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 516 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: 2.8951. Min Range: -2.8951

Max Act: 2.8951. Min Act: -0.1700

Data Index: 3522446 (Open Web Text)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.8258. Min Act: -0.1700

Data Index: 3838812 (Open Web Text)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.8196. Min Act: -0.1700

Data Index: 2452322 (Open Web Text)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.7665. Min Act: -0.1700

Data Index: 7421983 (Open Web Text)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.7122. Min Act: -0.1700

Data Index: 6521320 (Open Web Text)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.7198. Min Act: -0.1700

Data Index: 4589172 (Open Web Text)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.7093. Min Act: -0.1700

Data Index: 893027 (Open Web Text)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.7189. Min Act: -0.1700

Data Index: 7966624 (Open Web Text)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6930. Min Act: -0.1700

Data Index: 6020290 (Open Web Text)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6661. Min Act: -0.1700

Data Index: 878732 (Open Web Text)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6699. Min Act: -0.1700

Data Index: 3401258 (Open Web Text)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6808. Min Act: -0.1700

Data Index: 2024735 (Open Web Text)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6434. Min Act: -0.1700

Data Index: 8677227 (Open Web Text)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6429. Min Act: -0.1700

Data Index: 7629808 (Open Web Text)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6574. Min Act: -0.1700

Data Index: 3612673 (Open Web Text)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6289. Min Act: -0.1700

Data Index: 4988680 (Open Web Text)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6475. Min Act: -0.1700

Data Index: 430754 (Open Web Text)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6593. Min Act: -0.1700

Data Index: 8592987 (Open Web Text)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6392. Min Act: -0.1700

Data Index: 2956436 (Open Web Text)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8951. Min Range: -2.8951

Max Act: 2.6438. Min Act: -0.1700

Data Index: 3230806 (Open Web Text)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #19