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

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

Neuron 3380 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.4196. Min Act: -0.0003

Data Index: 77029 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3716. Min Act: -0.0003

Data Index: 416164 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3317. Min Act: -0.0003

Data Index: 812095 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3380. Min Act: -0.0003

Data Index: 705580 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3617. Min Act: -0.0003

Data Index: 1161086 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3271. Min Act: -0.0003

Data Index: 1011076 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3364. Min Act: -0.0003

Data Index: 1008636 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3251. Min Act: -0.0003

Data Index: 1229750 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3323. Min Act: -0.0003

Data Index: 487242 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3175. Min Act: -0.0003

Data Index: 922409 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3323. Min Act: -0.0003

Data Index: 1030371 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3211. Min Act: -0.0003

Data Index: 111027 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3179. Min Act: -0.0003

Data Index: 1148820 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3019. Min Act: -0.0003

Data Index: 319529 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.3083. Min Act: -0.0002

Data Index: 341727 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2920. Min Act: -0.0003

Data Index: 1211291 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2918. Min Act: -0.0003

Data Index: 1002915 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2918. Min Act: -0.0003

Data Index: 53590 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2951. Min Act: -0.0002

Data Index: 1061647 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.4196. Min Range: -0.4196

Max Act: 0.2960. Min Act: -0.0003

Data Index: 819130 (C4 (Web Text))

Max Activating Token Index: 748