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

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

Neuron 3359 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: 0.7148. Min Range: -0.7148

Max Act: 0.7148. Min Act: -0.0002

Data Index: 58324 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6771. Min Act: -0.0003

Data Index: 995906 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6299. Min Act: -0.0003

Data Index: 907769 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6486. Min Act: -0.0003

Data Index: 425030 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6449. Min Act: -0.0003

Data Index: 1025936 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6375. Min Act: -0.0003

Data Index: 868089 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6302. Min Act: -0.0003

Data Index: 400951 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6480. Min Act: -0.0003

Data Index: 923767 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6217. Min Act: -0.0003

Data Index: 760351 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6177. Min Act: -0.0003

Data Index: 486914 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5950. Min Act: -0.0003

Data Index: 56427 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6105. Min Act: -0.0003

Data Index: 770586 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5884. Min Act: -0.0003

Data Index: 1301867 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6083. Min Act: -0.0003

Data Index: 368028 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6034. Min Act: -0.0003

Data Index: 393032 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5826. Min Act: -0.0003

Data Index: 568950 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6232. Min Act: -0.0003

Data Index: 511342 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5827. Min Act: -0.0003

Data Index: 51998 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5985. Min Act: -0.0003

Data Index: 1044165 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6169. Min Act: -0.0003

Data Index: 954557 (C4 (Web Text))

Max Activating Token Index: 79