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

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

Neuron 2634 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.6966. Min Act: -0.0000

Data Index: 856580 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.4204. Min Act: -0.0000

Data Index: 366022 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.4092. Min Act: -0.0000

Data Index: 304870 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2519. Min Act: -0.0000

Data Index: 249912 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1675. Min Act: -0.0000

Data Index: 1008237 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2362. Min Act: -0.0000

Data Index: 817343 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2331. Min Act: -0.0000

Data Index: 77635 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2004. Min Act: -0.0000

Data Index: 261186 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2053. Min Act: -0.0000

Data Index: 1008394 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1338037 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1255. Min Act: -0.0000

Data Index: 291099 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1066. Min Act: -0.0000

Data Index: 843245 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1619. Min Act: -0.0000

Data Index: 300098 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1727. Min Act: -0.0000

Data Index: 527089 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1241861 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.2152. Min Act: -0.0000

Data Index: 637568 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1220. Min Act: -0.0000

Data Index: 975276 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1092. Min Act: -0.0000

Data Index: 1234844 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.1016. Min Act: -0.0000

Data Index: 429373 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 1.6966. Min Range: -1.6966

Max Act: 1.0347. Min Act: 0.0000

Data Index: 6301 (C4 (Web Text))

Max Activating Token Index: 417