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

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

Neuron 271 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2316. Min Act: -0.0002

Data Index: 326842 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2226. Min Act: -0.0002

Data Index: 826595 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2102. Min Act: -0.0002

Data Index: 410884 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2231. Min Act: -0.0002

Data Index: 746019 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2188. Min Act: -0.0002

Data Index: 502017 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2099. Min Act: -0.0002

Data Index: 134784 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2172. Min Act: -0.0002

Data Index: 1324926 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2207. Min Act: -0.0002

Data Index: 851633 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2051. Min Act: -0.0002

Data Index: 266663 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2044. Min Act: -0.0002

Data Index: 591459 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2048. Min Act: -0.0002

Data Index: 19235 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2032. Min Act: -0.0002

Data Index: 1333657 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2030. Min Act: -0.0002

Data Index: 1334497 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2094. Min Act: -0.0002

Data Index: 1228283 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1963. Min Act: -0.0002

Data Index: 125519 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2106. Min Act: -0.0002

Data Index: 440676 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1940. Min Act: -0.0002

Data Index: 466242 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1958. Min Act: -0.0002

Data Index: 558232 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2128. Min Act: -0.0002

Data Index: 1335531 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.2003. Min Act: -0.0002

Data Index: 991941 (C4 (Web Text))

Max Activating Token Index: 659