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

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

Neuron 2048 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2660. Min Act: -0.0001

Data Index: 106984 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2264. Min Act: -0.0000

Data Index: 685969 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1226594 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2312. Min Act: -0.0000

Data Index: 806940 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2166. Min Act: -0.0000

Data Index: 776327 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2244. Min Act: -0.0000

Data Index: 842507 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1202674 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2204. Min Act: -0.0000

Data Index: 397916 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2182. Min Act: -0.0000

Data Index: 53501 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2194. Min Act: -0.0000

Data Index: 184370 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2154. Min Act: -0.0000

Data Index: 497202 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2112. Min Act: -0.0000

Data Index: 920608 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2037. Min Act: -0.0000

Data Index: 808296 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2219. Min Act: -0.0000

Data Index: 613087 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1240592 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2116. Min Act: -0.0000

Data Index: 104919 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2040. Min Act: -0.0000

Data Index: 278958 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1971. Min Act: -0.0000

Data Index: 30904 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2024. Min Act: -0.0000

Data Index: 26322 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2081. Min Act: -0.0000

Data Index: 520232 (C4 (Web Text))

Max Activating Token Index: 19