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

Dataset: Open Web Text

Neuron 1984 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: 4.0362. Min Range: -4.0362

Max Act: 4.0362. Min Act: -0.1700

Data Index: 4316985 (Open Web Text)

Max Activating Token Index: 96

Text #1

Max Range: 4.0362. Min Range: -4.0362

Max Act: 4.0025. Min Act: -0.1700

Data Index: 5922879 (Open Web Text)

Max Activating Token Index: 446

Text #2

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9789. Min Act: -0.1700

Data Index: 8487864 (Open Web Text)

Max Activating Token Index: 170

Text #3

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9491. Min Act: -0.1700

Data Index: 1496179 (Open Web Text)

Max Activating Token Index: 801

Text #4

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9804. Min Act: -0.1700

Data Index: 4228082 (Open Web Text)

Max Activating Token Index: 467

Text #5

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9568. Min Act: -0.1700

Data Index: 2029138 (Open Web Text)

Max Activating Token Index: 188

Text #6

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9516. Min Act: -0.1700

Data Index: 6099332 (Open Web Text)

Max Activating Token Index: 457

Text #7

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9657. Min Act: -0.1700

Data Index: 1831358 (Open Web Text)

Max Activating Token Index: 980

Text #8

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9380. Min Act: -0.1700

Data Index: 4312443 (Open Web Text)

Max Activating Token Index: 810

Text #9

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9295. Min Act: -0.1700

Data Index: 4624349 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9420. Min Act: -0.1700

Data Index: 6969470 (Open Web Text)

Max Activating Token Index: 463

Text #11

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9366. Min Act: -0.1700

Data Index: 4098047 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9344. Min Act: -0.1700

Data Index: 6533469 (Open Web Text)

Max Activating Token Index: 435

Text #13

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9393. Min Act: -0.1700

Data Index: 118083 (Open Web Text)

Max Activating Token Index: 776

Text #14

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9409. Min Act: -0.1700

Data Index: 1448560 (Open Web Text)

Max Activating Token Index: 208

Text #15

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9439. Min Act: -0.1700

Data Index: 3328241 (Open Web Text)

Max Activating Token Index: 425

Text #16

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9142. Min Act: -0.1700

Data Index: 5543507 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9316. Min Act: -0.1700

Data Index: 2574093 (Open Web Text)

Max Activating Token Index: 819

Text #18

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9030. Min Act: -0.1700

Data Index: 1304457 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 4.0362. Min Range: -4.0362

Max Act: 3.9113. Min Act: -0.1700

Data Index: 1831354 (Open Web Text)

Max Activating Token Index: 333