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

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

Neuron 2427 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: 0.3619. Min Range: -0.3619

Max Act: 0.3619. Min Act: -0.0003

Data Index: 606287 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3591. Min Act: -0.0003

Data Index: 1164318 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3584. Min Act: -0.0003

Data Index: 222759 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3335. Min Act: -0.0003

Data Index: 1152853 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3126. Min Act: -0.0003

Data Index: 660852 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3204. Min Act: -0.0003

Data Index: 971492 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3186. Min Act: -0.0003

Data Index: 218729 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3114. Min Act: -0.0003

Data Index: 1176120 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3188. Min Act: -0.0003

Data Index: 850854 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2950. Min Act: -0.0002

Data Index: 24936 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2957. Min Act: -0.0003

Data Index: 1106637 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3035. Min Act: -0.0003

Data Index: 625170 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3005. Min Act: -0.0003

Data Index: 1175268 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3001. Min Act: -0.0003

Data Index: 1237652 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2989. Min Act: -0.0003

Data Index: 990889 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2882. Min Act: -0.0003

Data Index: 844064 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3077. Min Act: -0.0002

Data Index: 488398 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2862. Min Act: -0.0003

Data Index: 1311300 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2970. Min Act: -0.0003

Data Index: 63437 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2968. Min Act: -0.0003

Data Index: 552532 (C4 (Web Text))

Max Activating Token Index: 608