< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 453 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: 4.9959. Min Range: -4.9959

Max Act: 4.9959. Min Act: -0.1700

Data Index: 1756745 (Open Web Text)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.9482. Min Act: -0.1700

Data Index: 4512376 (Open Web Text)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.9372. Min Act: -0.1700

Data Index: 332749 (Open Web Text)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.9396. Min Act: -0.1700

Data Index: 5976250 (Open Web Text)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8774. Min Act: -0.1700

Data Index: 114679 (Open Web Text)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8897. Min Act: -0.1700

Data Index: 1826992 (Open Web Text)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8579. Min Act: -0.1700

Data Index: 2956029 (Open Web Text)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8755. Min Act: -0.1700

Data Index: 4445553 (Open Web Text)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8775. Min Act: -0.1700

Data Index: 8663103 (Open Web Text)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8294. Min Act: -0.1700

Data Index: 2630821 (Open Web Text)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8681. Min Act: -0.1700

Data Index: 2832323 (Open Web Text)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8554. Min Act: -0.1700

Data Index: 8186142 (Open Web Text)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8297. Min Act: -0.1700

Data Index: 2465908 (Open Web Text)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8366. Min Act: -0.1700

Data Index: 1733776 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8663. Min Act: -0.1700

Data Index: 737095 (Open Web Text)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8594. Min Act: -0.1700

Data Index: 2166365 (Open Web Text)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8287. Min Act: -0.1700

Data Index: 3371785 (Open Web Text)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8129. Min Act: -0.1700

Data Index: 3177020 (Open Web Text)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8186. Min Act: -0.1700

Data Index: 2545572 (Open Web Text)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.9959. Min Range: -4.9959

Max Act: 4.8148. Min Act: -0.1700

Data Index: 7161254 (Open Web Text)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #19