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

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

Neuron 2720 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: 0.5211. Min Range: -0.5211

Max Act: 0.5165. Min Act: -0.0000

Data Index: 846510 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.5174. Min Act: -0.0000

Data Index: 135089 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4733. Min Act: -0.0000

Data Index: 232006 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.5024. Min Act: -0.0000

Data Index: 832499 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.5211. Min Act: -0.0000

Data Index: 982393 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4807. Min Act: -0.0000

Data Index: 979656 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.5060. Min Act: -0.0000

Data Index: 88521 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1181286 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4651. Min Act: -0.0000

Data Index: 194871 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4603. Min Act: -0.0000

Data Index: 313225 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4428. Min Act: -0.0000

Data Index: 672501 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4686. Min Act: -0.0000

Data Index: 375210 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4524. Min Act: -0.0000

Data Index: 810954 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4459. Min Act: -0.0000

Data Index: 946375 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1060024 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1254735 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4349. Min Act: -0.0000

Data Index: 138123 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4049. Min Act: -0.0000

Data Index: 819174 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4210. Min Act: -0.0000

Data Index: 370655 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1094453 (C4 (Web Text))

Max Activating Token Index: 642