Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 450 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.7406. Min Act: -0.0002

Data Index: 268099 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.5076. Min Act: -0.0002

Data Index: 269883 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.4393. Min Act: -0.0002

Data Index: 166780 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.3636. Min Act: -0.0002

Data Index: 773778 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.2219. Min Act: -0.0002

Data Index: 364211 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.2306. Min Act: -0.0002

Data Index: 628288 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.1948. Min Act: -0.0002

Data Index: 525355 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.2136. Min Act: -0.0002

Data Index: 529370 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.2114. Min Act: -0.0002

Data Index: 5274 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.1211. Min Act: -0.0002

Data Index: 1086135 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.1092. Min Act: -0.0002

Data Index: 478248 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.0948. Min Act: -0.0002

Data Index: 11078 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.0353. Min Act: -0.0002

Data Index: 150915 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.0428. Min Act: -0.0002

Data Index: 265178 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.0656. Min Act: -0.0002

Data Index: 376475 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.0727. Min Act: -0.0002

Data Index: 978168 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.0594. Min Act: -0.0002

Data Index: 465093 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.0433. Min Act: -0.0002

Data Index: 85375 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.0761. Min Act: -0.0002

Data Index: 79943 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.7406. Min Range: -1.7406

Max Act: 1.0366. Min Act: -0.0002

Data Index: 1263645 (C4 (Web Text))

Max Activating Token Index: 22