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

Dataset: Open Web Text

Neuron 11 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: 3.2925. Min Range: -3.2925

Max Act: 3.2925. Min Act: -0.1700

Data Index: 1934988 (Open Web Text)

Max Activating Token Index: 537

Text #1

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.2287. Min Act: -0.1700

Data Index: 4794778 (Open Web Text)

Max Activating Token Index: 92

Text #2

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.2486. Min Act: -0.1700

Data Index: 7015492 (Open Web Text)

Max Activating Token Index: 853

Text #3

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1791. Min Act: -0.1700

Data Index: 2542094 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1989. Min Act: -0.1700

Data Index: 4242344 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1959. Min Act: -0.1700

Data Index: 5277208 (Open Web Text)

Max Activating Token Index: 704

Text #6

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1684. Min Act: -0.1700

Data Index: 4797001 (Open Web Text)

Max Activating Token Index: 855

Text #7

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1664. Min Act: -0.1700

Data Index: 7979070 (Open Web Text)

Max Activating Token Index: 488

Text #8

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1407. Min Act: -0.1700

Data Index: 3915083 (Open Web Text)

Max Activating Token Index: 786

Text #9

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1509. Min Act: -0.1700

Data Index: 545798 (Open Web Text)

Max Activating Token Index: 902

Text #10

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1547. Min Act: -0.1700

Data Index: 6859316 (Open Web Text)

Max Activating Token Index: 496

Text #11

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1555. Min Act: -0.1700

Data Index: 444454 (Open Web Text)

Max Activating Token Index: 426

Text #12

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1362. Min Act: -0.1700

Data Index: 4777169 (Open Web Text)

Max Activating Token Index: 467

Text #13

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1285. Min Act: -0.1700

Data Index: 1330493 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1505. Min Act: -0.1700

Data Index: 8597194 (Open Web Text)

Max Activating Token Index: 812

Text #15

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1431. Min Act: -0.1700

Data Index: 3294455 (Open Web Text)

Max Activating Token Index: 483

Text #16

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1319. Min Act: -0.1700

Data Index: 844037 (Open Web Text)

Max Activating Token Index: 515

Text #17

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1208. Min Act: -0.1700

Data Index: 6260457 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1326. Min Act: -0.1700

Data Index: 651759 (Open Web Text)

Max Activating Token Index: 161

Text #19

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1054. Min Act: -0.1700

Data Index: 3527775 (Open Web Text)

Max Activating Token Index: 610