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

Dataset: Open Web Text

Neuron 2493 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: 3.5065. Min Range: -3.5065

Max Act: 3.5065. Min Act: -0.1700

Data Index: 7434442 (Open Web Text)

Max Activating Token Index: 267

Text #1

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.4484. Min Act: -0.1700

Data Index: 412357 (Open Web Text)

Max Activating Token Index: 443

Text #2

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.2454. Min Act: -0.1700

Data Index: 7026723 (Open Web Text)

Max Activating Token Index: 855

Text #3

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.2144. Min Act: -0.1700

Data Index: 746855 (Open Web Text)

Max Activating Token Index: 248

Text #4

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1861. Min Act: -0.1700

Data Index: 4895002 (Open Web Text)

Max Activating Token Index: 766

Text #5

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1977. Min Act: -0.1700

Data Index: 2853824 (Open Web Text)

Max Activating Token Index: 505

Text #6

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1802. Min Act: -0.1700

Data Index: 8263275 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1476. Min Act: -0.1700

Data Index: 8639479 (Open Web Text)

Max Activating Token Index: 944

Text #8

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1907. Min Act: -0.1700

Data Index: 4587982 (Open Web Text)

Max Activating Token Index: 976

Text #9

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1333. Min Act: -0.1700

Data Index: 7156357 (Open Web Text)

Max Activating Token Index: 80

Text #10

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1227. Min Act: -0.1700

Data Index: 7516965 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1273. Min Act: -0.1700

Data Index: 8189002 (Open Web Text)

Max Activating Token Index: 636

Text #12

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1312. Min Act: -0.1700

Data Index: 5403740 (Open Web Text)

Max Activating Token Index: 537

Text #13

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1319. Min Act: -0.1700

Data Index: 6108986 (Open Web Text)

Max Activating Token Index: 226

Text #14

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.0875. Min Act: -0.1700

Data Index: 1021926 (Open Web Text)

Max Activating Token Index: 798

Text #15

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.0831. Min Act: -0.1700

Data Index: 5862717 (Open Web Text)

Max Activating Token Index: 146

Text #16

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.1318. Min Act: -0.1700

Data Index: 2716185 (Open Web Text)

Max Activating Token Index: 518

Text #17

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.0887. Min Act: -0.1700

Data Index: 393878 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.0995. Min Act: -0.1700

Data Index: 759123 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.0854. Min Act: -0.1700

Data Index: 6566226 (Open Web Text)

Max Activating Token Index: 534