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

Dataset: Open Web Text

Neuron 1261 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: 3.6720. Min Range: -3.6720

Max Act: 3.6670. Min Act: -0.1700

Data Index: 5029816 (Open Web Text)

Max Activating Token Index: 372

Text #1

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.6720. Min Act: -0.1700

Data Index: 4051944 (Open Web Text)

Max Activating Token Index: 45

Text #2

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.6237. Min Act: -0.1700

Data Index: 2101575 (Open Web Text)

Max Activating Token Index: 749

Text #3

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.4705. Min Act: -0.1700

Data Index: 697694 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.4319. Min Act: -0.1700

Data Index: 3904963 (Open Web Text)

Max Activating Token Index: 743

Text #5

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.5037. Min Act: -0.1700

Data Index: 3222206 (Open Web Text)

Max Activating Token Index: 960

Text #6

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3714. Min Act: -0.1700

Data Index: 6018582 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3861. Min Act: -0.1700

Data Index: 1343202 (Open Web Text)

Max Activating Token Index: 616

Text #8

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.4379. Min Act: -0.1700

Data Index: 6360795 (Open Web Text)

Max Activating Token Index: 340

Text #9

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.4378. Min Act: -0.1700

Data Index: 1313226 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3319. Min Act: -0.1700

Data Index: 5654664 (Open Web Text)

Max Activating Token Index: 228

Text #11

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3607. Min Act: -0.1700

Data Index: 2584386 (Open Web Text)

Max Activating Token Index: 1000

Text #12

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3492. Min Act: -0.1700

Data Index: 5562807 (Open Web Text)

Max Activating Token Index: 645

Text #13

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3669. Min Act: -0.1654

Data Index: 7149218 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3968. Min Act: -0.1700

Data Index: 436844 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3230. Min Act: -0.1700

Data Index: 1195651 (Open Web Text)

Max Activating Token Index: 420

Text #16

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3620. Min Act: -0.1700

Data Index: 8307764 (Open Web Text)

Max Activating Token Index: 101

Text #17

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3429. Min Act: -0.1700

Data Index: 6340157 (Open Web Text)

Max Activating Token Index: 469

Text #18

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.2005. Min Act: -0.1700

Data Index: 4425265 (Open Web Text)

Max Activating Token Index: 1015

Text #19

Max Range: 3.6720. Min Range: -3.6720

Max Act: 3.3194. Min Act: -0.1700

Data Index: 7099317 (Open Web Text)

Max Activating Token Index: 247