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

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

Neuron 284 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2178. Min Act: -0.0001

Data Index: 1241529 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1099641 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2219. Min Act: -0.0001

Data Index: 395812 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2138. Min Act: -0.0001

Data Index: 1277738 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2186. Min Act: -0.0001

Data Index: 890040 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2110. Min Act: -0.0001

Data Index: 472869 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2209. Min Act: -0.0001

Data Index: 1355258 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1233293 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1870. Min Act: -0.0001

Data Index: 872610 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1973. Min Act: -0.0001

Data Index: 3274 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2021. Min Act: -0.0001

Data Index: 792010 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1821. Min Act: -0.0001

Data Index: 130182 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1927. Min Act: -0.0001

Data Index: 1330661 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1954. Min Act: -0.0001

Data Index: 203088 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2009. Min Act: -0.0001

Data Index: 1036335 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1800. Min Act: -0.0001

Data Index: 817914 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1895. Min Act: -0.0001

Data Index: 684149 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2009. Min Act: -0.0001

Data Index: 1197668 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1922. Min Act: -0.0001

Data Index: 816635 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1130204 (C4 (Web Text))

Max Activating Token Index: 617