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

Dataset: Open Web Text

Neuron 865 in Layer 6

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: 4.6321. Min Range: -4.6321

Max Act: 4.6321. Min Act: -0.1700

Data Index: 4423135 (Open Web Text)

Max Activating Token Index: 618

Text #1

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.6238. Min Act: -0.1700

Data Index: 3143102 (Open Web Text)

Max Activating Token Index: 303

Text #2

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.6302. Min Act: -0.1700

Data Index: 6455433 (Open Web Text)

Max Activating Token Index: 881

Text #3

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.6237. Min Act: -0.1700

Data Index: 6111871 (Open Web Text)

Max Activating Token Index: 781

Text #4

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.5648. Min Act: -0.1700

Data Index: 763155 (Open Web Text)

Max Activating Token Index: 303

Text #5

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.5138. Min Act: -0.1700

Data Index: 6139932 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.5482. Min Act: -0.1700

Data Index: 2624476 (Open Web Text)

Max Activating Token Index: 575

Text #7

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.4133. Min Act: -0.1700

Data Index: 1890919 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.4596. Min Act: -0.1700

Data Index: 2697529 (Open Web Text)

Max Activating Token Index: 653

Text #9

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.4308. Min Act: -0.1700

Data Index: 7275493 (Open Web Text)

Max Activating Token Index: 856

Text #10

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.3547. Min Act: -0.1700

Data Index: 7640429 (Open Web Text)

Max Activating Token Index: 684

Text #11

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.4117. Min Act: -0.1700

Data Index: 2406962 (Open Web Text)

Max Activating Token Index: 712

Text #12

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.4350. Min Act: -0.1700

Data Index: 3754507 (Open Web Text)

Max Activating Token Index: 595

Text #13

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.4536. Min Act: -0.1700

Data Index: 7867711 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.4106. Min Act: -0.1700

Data Index: 7757140 (Open Web Text)

Max Activating Token Index: 495

Text #15

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.3642. Min Act: -0.1700

Data Index: 1418005 (Open Web Text)

Max Activating Token Index: 218

Text #16

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.3195. Min Act: -0.1700

Data Index: 795048 (Open Web Text)

Max Activating Token Index: 757

Text #17

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.3543. Min Act: -0.1700

Data Index: 4189735 (Open Web Text)

Max Activating Token Index: 983

Text #18

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.3445. Min Act: -0.1700

Data Index: 4702786 (Open Web Text)

Max Activating Token Index: 645

Text #19

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.3138. Min Act: -0.1700

Data Index: 337741 (Open Web Text)

Max Activating Token Index: 216