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

Dataset: Open Web Text

Neuron 1108 in Layer 1

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: 1.9949. Min Range: -1.9949

Max Act: 1.9949. Min Act: -0.1700

Data Index: 3091717 (Open Web Text)

Max Activating Token Index: 640

Text #1

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9913. Min Act: -0.1700

Data Index: 5769701 (Open Web Text)

Max Activating Token Index: 338

Text #2

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9824. Min Act: -0.1700

Data Index: 1995389 (Open Web Text)

Max Activating Token Index: 426

Text #3

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9490. Min Act: -0.1700

Data Index: 6945531 (Open Web Text)

Max Activating Token Index: 28

Text #4

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9535. Min Act: -0.1700

Data Index: 4826171 (Open Web Text)

Max Activating Token Index: 104

Text #5

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9591. Min Act: -0.1700

Data Index: 3097701 (Open Web Text)

Max Activating Token Index: 115

Text #6

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9508. Min Act: -0.1700

Data Index: 8403254 (Open Web Text)

Max Activating Token Index: 30

Text #7

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9636. Min Act: -0.1700

Data Index: 273176 (Open Web Text)

Max Activating Token Index: 630

Text #8

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9332. Min Act: -0.1700

Data Index: 6464312 (Open Web Text)

Max Activating Token Index: 229

Text #9

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9352. Min Act: -0.1700

Data Index: 2017120 (Open Web Text)

Max Activating Token Index: 27

Text #10

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9348. Min Act: -0.1700

Data Index: 4197945 (Open Web Text)

Max Activating Token Index: 588

Text #11

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9300. Min Act: -0.1700

Data Index: 2739350 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9386. Min Act: -0.1700

Data Index: 5745356 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9504. Min Act: -0.1700

Data Index: 8606090 (Open Web Text)

Max Activating Token Index: 545

Text #14

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9388. Min Act: -0.1700

Data Index: 7564555 (Open Web Text)

Max Activating Token Index: 296

Text #15

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9357. Min Act: -0.1700

Data Index: 3015392 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9356. Min Act: -0.1700

Data Index: 1485471 (Open Web Text)

Max Activating Token Index: 94

Text #17

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9357. Min Act: -0.1700

Data Index: 3921674 (Open Web Text)

Max Activating Token Index: 543

Text #18

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9156. Min Act: -0.1700

Data Index: 3428180 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 1.9949. Min Range: -1.9949

Max Act: 1.9156. Min Act: -0.1700

Data Index: 4173247 (Open Web Text)

Max Activating Token Index: 77