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

Dataset: Open Web Text

Neuron 281 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: 3.4950. Min Range: -3.4950

Max Act: 3.4950. Min Act: -0.1700

Data Index: 3188204 (Open Web Text)

Max Activating Token Index: 855

Text #1

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.4671. Min Act: -0.1700

Data Index: 5965580 (Open Web Text)

Max Activating Token Index: 1003

Text #2

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.4617. Min Act: -0.1700

Data Index: 3943423 (Open Web Text)

Max Activating Token Index: 883

Text #3

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.4558. Min Act: -0.1700

Data Index: 3943431 (Open Web Text)

Max Activating Token Index: 976

Text #4

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.4305. Min Act: -0.1700

Data Index: 3943426 (Open Web Text)

Max Activating Token Index: 539

Text #5

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3918. Min Act: -0.1700

Data Index: 3943445 (Open Web Text)

Max Activating Token Index: 442

Text #6

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.4134. Min Act: -0.1700

Data Index: 3943425 (Open Web Text)

Max Activating Token Index: 707

Text #7

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3949. Min Act: -0.1700

Data Index: 3943437 (Open Web Text)

Max Activating Token Index: 934

Text #8

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.4084. Min Act: -0.1700

Data Index: 3943436 (Open Web Text)

Max Activating Token Index: 994

Text #9

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3923. Min Act: -0.1700

Data Index: 3943422 (Open Web Text)

Max Activating Token Index: 838

Text #10

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3741. Min Act: -0.1700

Data Index: 3943440 (Open Web Text)

Max Activating Token Index: 974

Text #11

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3453. Min Act: -0.1700

Data Index: 3943442 (Open Web Text)

Max Activating Token Index: 802

Text #12

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3803. Min Act: -0.1700

Data Index: 3943435 (Open Web Text)

Max Activating Token Index: 732

Text #13

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3518. Min Act: -0.1700

Data Index: 3943432 (Open Web Text)

Max Activating Token Index: 868

Text #14

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3532. Min Act: -0.1700

Data Index: 3943428 (Open Web Text)

Max Activating Token Index: 940

Text #15

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3514. Min Act: -0.1700

Data Index: 951833 (Open Web Text)

Max Activating Token Index: 407

Text #16

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3384. Min Act: -0.1700

Data Index: 951832 (Open Web Text)

Max Activating Token Index: 444

Text #17

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3383. Min Act: -0.1700

Data Index: 3943427 (Open Web Text)

Max Activating Token Index: 881

Text #18

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3273. Min Act: -0.1700

Data Index: 181422 (Open Web Text)

Max Activating Token Index: 469

Text #19

Max Range: 3.4950. Min Range: -3.4950

Max Act: 3.3106. Min Act: -0.1700

Data Index: 3943443 (Open Web Text)

Max Activating Token Index: 668