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

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

Neuron 2495 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1294636 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2415. Min Act: -0.0000

Data Index: 114093 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1091012 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2539. Min Act: -0.0000

Data Index: 251665 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1075185 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2324. Min Act: -0.0000

Data Index: 932623 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2305. Min Act: -0.0000

Data Index: 92235 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1213594 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2297. Min Act: -0.0000

Data Index: 627925 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1201468 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2135. Min Act: -0.0000

Data Index: 667766 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2150. Min Act: -0.0000

Data Index: 734146 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1309114 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2152. Min Act: -0.0000

Data Index: 386375 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2113. Min Act: -0.0000

Data Index: 55505 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2122. Min Act: -0.0000

Data Index: 218537 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2170. Min Act: -0.0000

Data Index: 111615 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2088. Min Act: -0.0000

Data Index: 498897 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2080. Min Act: -0.0000

Data Index: 711194 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1934. Min Act: -0.0000

Data Index: 626076 (C4 (Web Text))

Max Activating Token Index: 769