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

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

Neuron 1168 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4842. Min Act: -0.0002

Data Index: 1349857 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4630. Min Act: -0.0002

Data Index: 976605 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4690. Min Act: -0.0002

Data Index: 178187 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4292. Min Act: -0.0002

Data Index: 465604 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4316. Min Act: -0.0002

Data Index: 1105084 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4298. Min Act: -0.0002

Data Index: 45683 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4282. Min Act: -0.0002

Data Index: 485297 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4429. Min Act: -0.0002

Data Index: 463989 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4227. Min Act: -0.0002

Data Index: 658008 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4293. Min Act: -0.0002

Data Index: 4175 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4268. Min Act: -0.0002

Data Index: 983579 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4234. Min Act: -0.0002

Data Index: 170836 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4263. Min Act: -0.0002

Data Index: 657389 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4176. Min Act: -0.0002

Data Index: 1114134 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4008. Min Act: -0.0002

Data Index: 147182 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4106. Min Act: -0.0002

Data Index: 283535 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4077. Min Act: -0.0002

Data Index: 969656 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4251. Min Act: -0.0002

Data Index: 357512 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4068. Min Act: -0.0002

Data Index: 920568 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3680. Min Act: -0.0002

Data Index: 1341298 (C4 (Web Text))

Max Activating Token Index: 158