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

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

Neuron 3871 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.3337. Min Act: -0.0000

Data Index: 428411 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1275516 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.3055. Min Act: -0.0000

Data Index: 95062 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2852. Min Act: -0.0000

Data Index: 712925 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1214370 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2743. Min Act: -0.0000

Data Index: 382729 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2627. Min Act: -0.0000

Data Index: 975773 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2497. Min Act: -0.0000

Data Index: 328288 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2498. Min Act: -0.0000

Data Index: 407907 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1046317 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2547. Min Act: -0.0000

Data Index: 484879 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2439. Min Act: -0.0000

Data Index: 708821 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2488. Min Act: -0.0000

Data Index: 424626 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2430. Min Act: -0.0000

Data Index: 244487 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2463. Min Act: -0.0000

Data Index: 568757 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2223. Min Act: -0.0000

Data Index: 954505 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2068. Min Act: -0.0000

Data Index: 732492 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1023259 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1138835 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2214. Min Act: -0.0000

Data Index: 447842 (C4 (Web Text))

Max Activating Token Index: 529