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

Dataset: Open Web Text

Neuron 510 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: 3.8001. Min Range: -3.8001

Max Act: 3.8001. Min Act: -0.1700

Data Index: 8744020 (Open Web Text)

Max Activating Token Index: 219

Text #1

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.7603. Min Act: -0.1700

Data Index: 6300001 (Open Web Text)

Max Activating Token Index: 119

Text #2

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.7196. Min Act: -0.1700

Data Index: 2816419 (Open Web Text)

Max Activating Token Index: 681

Text #3

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.7204. Min Act: -0.1700

Data Index: 255126 (Open Web Text)

Max Activating Token Index: 826

Text #4

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.7283. Min Act: -0.1700

Data Index: 2215976 (Open Web Text)

Max Activating Token Index: 337

Text #5

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.7313. Min Act: -0.1700

Data Index: 2314402 (Open Web Text)

Max Activating Token Index: 25

Text #6

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.7342. Min Act: -0.1700

Data Index: 5422894 (Open Web Text)

Max Activating Token Index: 607

Text #7

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.7005. Min Act: -0.1700

Data Index: 887233 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.7328. Min Act: -0.1700

Data Index: 7458552 (Open Web Text)

Max Activating Token Index: 908

Text #9

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.6885. Min Act: -0.1700

Data Index: 2410324 (Open Web Text)

Max Activating Token Index: 861

Text #10

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.7310. Min Act: -0.1700

Data Index: 6932383 (Open Web Text)

Max Activating Token Index: 189

Text #11

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.7215. Min Act: -0.1700

Data Index: 6460211 (Open Web Text)

Max Activating Token Index: 665

Text #12

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.6626. Min Act: -0.1700

Data Index: 7818034 (Open Web Text)

Max Activating Token Index: 420

Text #13

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.6732. Min Act: -0.1700

Data Index: 3584417 (Open Web Text)

Max Activating Token Index: 824

Text #14

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.6581. Min Act: -0.1700

Data Index: 5686468 (Open Web Text)

Max Activating Token Index: 565

Text #15

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.6923. Min Act: -0.1700

Data Index: 144024 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.6267. Min Act: -0.1700

Data Index: 2870833 (Open Web Text)

Max Activating Token Index: 599

Text #17

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.6405. Min Act: -0.1700

Data Index: 5242505 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.6472. Min Act: -0.1700

Data Index: 4237889 (Open Web Text)

Max Activating Token Index: 543

Text #19

Max Range: 3.8001. Min Range: -3.8001

Max Act: 3.6372. Min Act: -0.1700

Data Index: 7885131 (Open Web Text)

Max Activating Token Index: 770