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

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

Neuron 40 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.4586. Min Range: -11.4586

Max Act: 11.4586. Min Act: -0.0002

Data Index: 173664 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 11.4586. Min Range: -11.4586

Max Act: 7.1320. Min Act: -0.0002

Data Index: 1125108 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.5622. Min Act: -0.0002

Data Index: 908197 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.4654. Min Act: -0.0002

Data Index: 482806 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.2673. Min Act: -0.0002

Data Index: 1299099 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.4704. Min Act: -0.0002

Data Index: 205229 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.2845. Min Act: -0.0002

Data Index: 687547 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.0259. Min Act: -0.0002

Data Index: 976884 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.0941. Min Act: -0.0002

Data Index: 185299 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.0199. Min Act: -0.0002

Data Index: 481761 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.0337. Min Act: -0.0002

Data Index: 67417 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.4466. Min Act: -0.0002

Data Index: 373942 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 11.4586. Min Range: -11.4586

Max Act: 5.0164. Min Act: -0.0002

Data Index: 1137543 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 11.4586. Min Range: -11.4586

Max Act: 4.7208. Min Act: -0.0002

Data Index: 458670 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 11.4586. Min Range: -11.4586

Max Act: 4.6476. Min Act: -0.0002

Data Index: 444519 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 11.4586. Min Range: -11.4586

Max Act: 4.3928. Min Act: -0.0002

Data Index: 807500 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 11.4586. Min Range: -11.4586

Max Act: 4.5992. Min Act: -0.0002

Data Index: 550677 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 11.4586. Min Range: -11.4586

Max Act: 4.7416. Min Act: -0.0002

Data Index: 478249 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 11.4586. Min Range: -11.4586

Max Act: 4.5221. Min Act: -0.0002

Data Index: 1301372 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 11.4586. Min Range: -11.4586

Max Act: 4.5318. Min Act: -0.0002

Data Index: 178523 (C4 (Web Text))

Max Activating Token Index: 256