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

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

Neuron 4127 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1074267 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2241. Min Act: -0.0000

Data Index: 941940 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2277. Min Act: -0.0000

Data Index: 888205 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2173. Min Act: -0.0000

Data Index: 344066 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1225853 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2150. Min Act: -0.0000

Data Index: 30318 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2084. Min Act: -0.0000

Data Index: 440648 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2157. Min Act: -0.0000

Data Index: 974412 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1236933 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2005. Min Act: -0.0000

Data Index: 991812 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2078. Min Act: -0.0000

Data Index: 143924 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2043. Min Act: -0.0000

Data Index: 254336 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1968. Min Act: -0.0001

Data Index: 274511 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1805. Min Act: -0.0000

Data Index: 411356 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1127659 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1120980 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2062. Min Act: -0.0000

Data Index: 654608 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1072214 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1921. Min Act: -0.0000

Data Index: 738331 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2064. Min Act: -0.0000

Data Index: 134317 (C4 (Web Text))

Max Activating Token Index: 70