Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 405 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.6185. Min Act: -0.0003

Data Index: 1149677 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.5657. Min Act: -0.0003

Data Index: 567606 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.5613. Min Act: -0.0003

Data Index: 1065498 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.5223. Min Act: -0.0003

Data Index: 1345580 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.5295. Min Act: -0.0003

Data Index: 776773 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4939. Min Act: -0.0003

Data Index: 942391 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4976. Min Act: -0.0003

Data Index: 432282 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4608. Min Act: -0.0003

Data Index: 102589 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4686. Min Act: -0.0003

Data Index: 535444 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4547. Min Act: -0.0003

Data Index: 616623 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4373. Min Act: -0.0003

Data Index: 955556 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4662. Min Act: -0.0003

Data Index: 121823 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4653. Min Act: -0.0003

Data Index: 1106477 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4621. Min Act: -0.0003

Data Index: 1321024 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4227. Min Act: -0.0003

Data Index: 898721 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4413. Min Act: -0.0003

Data Index: 1163222 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4412. Min Act: -0.0003

Data Index: 1207932 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4346. Min Act: -0.0003

Data Index: 1092353 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4285. Min Act: -0.0003

Data Index: 1061502 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.6185. Min Range: -0.6185

Max Act: 0.4173. Min Act: -0.0003

Data Index: 1087049 (C4 (Web Text))

Max Activating Token Index: 123