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

Dataset: Open Web Text

Neuron 2704 in Layer 3

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: 3.5518. Min Range: -3.5518

Max Act: 3.5518. Min Act: -0.1700

Data Index: 7599065 (Open Web Text)

Max Activating Token Index: 861

Text #1

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.4445. Min Act: -0.1700

Data Index: 5314126 (Open Web Text)

Max Activating Token Index: 279

Text #2

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.4177. Min Act: -0.1700

Data Index: 161881 (Open Web Text)

Max Activating Token Index: 158

Text #3

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.4185. Min Act: -0.1700

Data Index: 2867719 (Open Web Text)

Max Activating Token Index: 634

Text #4

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3918. Min Act: -0.1700

Data Index: 441981 (Open Web Text)

Max Activating Token Index: 597

Text #5

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3737. Min Act: -0.1700

Data Index: 3038521 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3724. Min Act: -0.1700

Data Index: 7105655 (Open Web Text)

Max Activating Token Index: 78

Text #7

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3504. Min Act: -0.1700

Data Index: 7693490 (Open Web Text)

Max Activating Token Index: 255

Text #8

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3664. Min Act: -0.1700

Data Index: 4572902 (Open Web Text)

Max Activating Token Index: 501

Text #9

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3502. Min Act: -0.1700

Data Index: 1717109 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3456. Min Act: -0.1700

Data Index: 7105656 (Open Web Text)

Max Activating Token Index: 422

Text #11

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3416. Min Act: -0.1700

Data Index: 7617474 (Open Web Text)

Max Activating Token Index: 434

Text #12

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3354. Min Act: -0.1700

Data Index: 2727151 (Open Web Text)

Max Activating Token Index: 736

Text #13

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3305. Min Act: -0.1700

Data Index: 6148594 (Open Web Text)

Max Activating Token Index: 412

Text #14

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3366. Min Act: -0.1700

Data Index: 1234698 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3327. Min Act: -0.1700

Data Index: 2054786 (Open Web Text)

Max Activating Token Index: 750

Text #16

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3109. Min Act: -0.1700

Data Index: 790591 (Open Web Text)

Max Activating Token Index: 557

Text #17

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3097. Min Act: -0.1700

Data Index: 5895511 (Open Web Text)

Max Activating Token Index: 351

Text #18

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.3041. Min Act: -0.1700

Data Index: 6212210 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 3.5518. Min Range: -3.5518

Max Act: 3.2999. Min Act: -0.1700

Data Index: 1355525 (Open Web Text)

Max Activating Token Index: 90