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

Dataset: Open Web Text

Neuron 945 in Layer 5

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: 4.5319. Min Range: -4.5319

Max Act: 4.5319. Min Act: -0.1700

Data Index: 814719 (Open Web Text)

Max Activating Token Index: 297

Text #1

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.5136. Min Act: -0.1700

Data Index: 7428496 (Open Web Text)

Max Activating Token Index: 886

Text #2

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4853. Min Act: -0.1698

Data Index: 7265434 (Open Web Text)

Max Activating Token Index: 815

Text #3

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4414. Min Act: -0.1700

Data Index: 1587436 (Open Web Text)

Max Activating Token Index: 209

Text #4

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4239. Min Act: -0.1700

Data Index: 7646603 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3875. Min Act: -0.1700

Data Index: 2562148 (Open Web Text)

Max Activating Token Index: 469

Text #6

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3732. Min Act: -0.1700

Data Index: 5736769 (Open Web Text)

Max Activating Token Index: 756

Text #7

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3697. Min Act: -0.1700

Data Index: 652735 (Open Web Text)

Max Activating Token Index: 318

Text #8

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3666. Min Act: -0.1700

Data Index: 4779132 (Open Web Text)

Max Activating Token Index: 972

Text #9

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3698. Min Act: -0.1700

Data Index: 7339098 (Open Web Text)

Max Activating Token Index: 443

Text #10

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3583. Min Act: -0.1700

Data Index: 7252675 (Open Web Text)

Max Activating Token Index: 251

Text #11

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3392. Min Act: -0.1700

Data Index: 8399706 (Open Web Text)

Max Activating Token Index: 80

Text #12

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3787. Min Act: -0.1700

Data Index: 5672329 (Open Web Text)

Max Activating Token Index: 508

Text #13

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3708. Min Act: -0.1700

Data Index: 2643554 (Open Web Text)

Max Activating Token Index: 534

Text #14

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3491. Min Act: -0.1700

Data Index: 5095903 (Open Web Text)

Max Activating Token Index: 291

Text #15

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3662. Min Act: -0.1700

Data Index: 1311557 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3458. Min Act: -0.1700

Data Index: 7159066 (Open Web Text)

Max Activating Token Index: 268

Text #17

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3186. Min Act: -0.1700

Data Index: 1104977 (Open Web Text)

Max Activating Token Index: 332

Text #18

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.2987. Min Act: -0.1700

Data Index: 1411798 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3340. Min Act: -0.1700

Data Index: 1502786 (Open Web Text)

Max Activating Token Index: 93