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

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

Neuron 4900 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: 0.4248. Min Range: -0.4248

Max Act: 0.4230. Min Act: 0.0000

Data Index: 133933 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1021703 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1317088 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.4023. Min Act: -0.0000

Data Index: 621704 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3678. Min Act: -0.0000

Data Index: 222845 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3493. Min Act: -0.0000

Data Index: 202248 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3268. Min Act: -0.0000

Data Index: 171992 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3223. Min Act: -0.0000

Data Index: 395615 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3191. Min Act: 0.0000

Data Index: 565212 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3021. Min Act: -0.0000

Data Index: 30553 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3133. Min Act: -0.0000

Data Index: 483731 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1123749 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3042. Min Act: -0.0000

Data Index: 721401 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3024. Min Act: -0.0000

Data Index: 956259 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2733. Min Act: -0.0000

Data Index: 324732 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2809. Min Act: -0.0000

Data Index: 774020 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2902. Min Act: -0.0000

Data Index: 620700 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1312816 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2953. Min Act: -0.0000

Data Index: 109277 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2759. Min Act: -0.0000

Data Index: 855105 (C4 (Web Text))

Max Activating Token Index: 623