Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1208 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.8470. Min Act: -0.0000

Data Index: 726164 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.8021. Min Act: -0.0000

Data Index: 847790 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.8168. Min Act: -0.0000

Data Index: 380605 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.8463. Min Act: -0.0000

Data Index: 807285 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7562. Min Act: -0.0000

Data Index: 156239 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7983. Min Act: -0.0000

Data Index: 334957 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1357812 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7374. Min Act: -0.0000

Data Index: 674912 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1284006 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1147468 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7133. Min Act: -0.0000

Data Index: 220466 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7078. Min Act: -0.0000

Data Index: 321683 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6765. Min Act: -0.0000

Data Index: 289930 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6370. Min Act: -0.0000

Data Index: 456034 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6352. Min Act: -0.0000

Data Index: 306175 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6284. Min Act: -0.0000

Data Index: 445919 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6266. Min Act: -0.0000

Data Index: 412 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5864. Min Act: -0.0000

Data Index: 443141 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1029861 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6622. Min Act: -0.0000

Data Index: 607094 (C4 (Web Text))

Max Activating Token Index: 184