Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3896 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2858. Min Act: -0.0001

Data Index: 361859 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2641. Min Act: -0.0001

Data Index: 629245 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2158. Min Act: -0.0001

Data Index: 283766 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2044. Min Act: -0.0000

Data Index: 161393 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2249. Min Act: -0.0001

Data Index: 200450 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2072. Min Act: -0.0001

Data Index: 432807 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2198. Min Act: -0.0000

Data Index: 313384 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2000. Min Act: -0.0001

Data Index: 142633 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2038. Min Act: -0.0000

Data Index: 191327 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2172. Min Act: -0.0001

Data Index: 249204 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.1895. Min Act: -0.0001

Data Index: 56423 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2037. Min Act: -0.0001

Data Index: 1022938 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.1993. Min Act: -0.0000

Data Index: 364365 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2008. Min Act: -0.0001

Data Index: 241260 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1323004 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.1896. Min Act: -0.0000

Data Index: 82666 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.1864. Min Act: -0.0001

Data Index: 59844 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.1987. Min Act: -0.0000

Data Index: 987980 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1097139 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.1893. Min Act: -0.0000

Data Index: 352146 (C4 (Web Text))

Max Activating Token Index: 15