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

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

Neuron 2916 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1199353 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.3058. Min Act: -0.0000

Data Index: 363269 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2931. Min Act: -0.0000

Data Index: 417912 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2946. Min Act: -0.0000

Data Index: 426588 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1086028 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2944. Min Act: -0.0000

Data Index: 83327 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2848. Min Act: -0.0000

Data Index: 601905 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1018334 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2609. Min Act: -0.0000

Data Index: 716013 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2582. Min Act: -0.0000

Data Index: 690397 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2391. Min Act: -0.0000

Data Index: 810943 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1037302 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2560. Min Act: -0.0000

Data Index: 78312 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1023831 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2272. Min Act: -0.0000

Data Index: 414824 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2463. Min Act: -0.0000

Data Index: 603610 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1250717 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2445. Min Act: -0.0000

Data Index: 712942 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2449. Min Act: -0.0000

Data Index: 329174 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2327. Min Act: -0.0000

Data Index: 547065 (C4 (Web Text))

Max Activating Token Index: 158