Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2469 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0059. Min Act: -0.0002

Data Index: 732038 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0002

Data Index: 686240 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 827451 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0048. Min Act: -0.0002

Data Index: 430377 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1440083 (Python Code)

Max Activating Token Index: 854

Text #5

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0047. Min Act: -0.0002

Data Index: 95188 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0046. Min Act: -0.0002

Data Index: 80222 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1171181 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0045. Min Act: -0.0002

Data Index: 261147 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0045. Min Act: -0.0002

Data Index: 896447 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0044. Min Act: -0.0002

Data Index: 142794 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0044. Min Act: -0.0002

Data Index: 550839 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0044. Min Act: -0.0002

Data Index: 627991 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1215009 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0043. Min Act: -0.0002

Data Index: 546270 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1157474 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0042. Min Act: -0.0002

Data Index: 315164 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0042. Min Act: -0.0002

Data Index: 736116 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0042. Min Act: -0.0002

Data Index: 5869 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0042. Min Act: -0.0002

Data Index: 1217642 (C4 (Web Text))

Max Activating Token Index: 618