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

Dataset: Open Web Text

Neuron 1471 in Layer 0

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: 3.6470. Min Range: -3.6470

Max Act: 3.6421. Min Act: -0.1700

Data Index: 8685666 (Open Web Text)

Max Activating Token Index: 815

Text #1

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.6470. Min Act: -0.1700

Data Index: 3560729 (Open Web Text)

Max Activating Token Index: 402

Text #2

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.6354. Min Act: -0.1700

Data Index: 3527312 (Open Web Text)

Max Activating Token Index: 128

Text #3

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5858. Min Act: -0.1700

Data Index: 3046704 (Open Web Text)

Max Activating Token Index: 120

Text #4

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5482. Min Act: -0.1700

Data Index: 8816077 (Open Web Text)

Max Activating Token Index: 60

Text #5

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5639. Min Act: -0.1700

Data Index: 2481645 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5760. Min Act: -0.1700

Data Index: 6579164 (Open Web Text)

Max Activating Token Index: 661

Text #7

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5637. Min Act: -0.1700

Data Index: 3441225 (Open Web Text)

Max Activating Token Index: 809

Text #8

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5461. Min Act: -0.1700

Data Index: 542413 (Open Web Text)

Max Activating Token Index: 302

Text #9

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5465. Min Act: -0.1700

Data Index: 625308 (Open Web Text)

Max Activating Token Index: 696

Text #10

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5188. Min Act: -0.1700

Data Index: 7560836 (Open Web Text)

Max Activating Token Index: 553

Text #11

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5475. Min Act: -0.1700

Data Index: 2890965 (Open Web Text)

Max Activating Token Index: 350

Text #12

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5386. Min Act: -0.1700

Data Index: 6342373 (Open Web Text)

Max Activating Token Index: 582

Text #13

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5378. Min Act: -0.1700

Data Index: 2858870 (Open Web Text)

Max Activating Token Index: 27

Text #14

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5157. Min Act: -0.1700

Data Index: 542415 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5534. Min Act: -0.1700

Data Index: 5853707 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5304. Min Act: -0.1700

Data Index: 529568 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5152. Min Act: -0.1700

Data Index: 5387058 (Open Web Text)

Max Activating Token Index: 700

Text #18

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5479. Min Act: -0.1700

Data Index: 4287022 (Open Web Text)

Max Activating Token Index: 514

Text #19

Max Range: 3.6470. Min Range: -3.6470

Max Act: 3.5194. Min Act: -0.1700

Data Index: 2377659 (Open Web Text)

Max Activating Token Index: 874