Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2022 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1303271 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6191. Min Act: -0.0000

Data Index: 735295 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6070. Min Act: -0.0000

Data Index: 720038 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5764. Min Act: -0.0000

Data Index: 24806 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5511. Min Act: -0.0000

Data Index: 782897 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1334297 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1207706 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1523204 (Python Code)

Max Activating Token Index: 930

Text #8

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1541719 (Python Code)

Max Activating Token Index: 961

Text #9

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4924. Min Act: -0.0000

Data Index: 597906 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4886. Min Act: -0.0000

Data Index: 907272 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4809. Min Act: -0.0000

Data Index: 13946 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4803. Min Act: -0.0000

Data Index: 675188 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4809. Min Act: -0.0000

Data Index: 209848 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1273929 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4961. Min Act: -0.0000

Data Index: 399660 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4953. Min Act: -0.0000

Data Index: 395327 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4837. Min Act: -0.0000

Data Index: 117281 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4995. Min Act: -0.0000

Data Index: 374650 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.4597. Min Act: -0.0000

Data Index: 880109 (C4 (Web Text))

Max Activating Token Index: 488