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

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

Neuron 379 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1246579 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2478. Min Act: -0.0000

Data Index: 954193 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2560. Min Act: -0.0000

Data Index: 867210 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2335. Min Act: -0.0000

Data Index: 389682 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1123833 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1330207 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2316. Min Act: -0.0000

Data Index: 453112 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2293. Min Act: -0.0000

Data Index: 213912 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1867. Min Act: -0.0000

Data Index: 308872 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2175. Min Act: -0.0000

Data Index: 408390 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1360752 (Python Code)

Max Activating Token Index: 704

Text #11

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2243. Min Act: -0.0000

Data Index: 412235 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1453003 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1439230 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2155. Min Act: -0.0000

Data Index: 848903 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.1988. Min Act: -0.0000

Data Index: 699873 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1044937 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1288878 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2007. Min Act: -0.0000

Data Index: 79727 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2283. Min Act: -0.0000

Data Index: 191653 (C4 (Web Text))

Max Activating Token Index: 262