Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 394 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1110. Min Act: -0.0003

Data Index: 475024 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0798. Min Act: -0.0004

Data Index: 399160 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0809. Min Act: -0.0003

Data Index: 266801 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0615. Min Act: -0.0003

Data Index: 305010 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1208630 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1032396 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0610. Min Act: -0.0002

Data Index: 712177 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0557. Min Act: -0.0003

Data Index: 839128 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0610. Min Act: -0.0003

Data Index: 129315 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0596. Min Act: -0.0003

Data Index: 149161 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0554. Min Act: -0.0003

Data Index: 100914 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0555. Min Act: -0.0003

Data Index: 894218 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1170342 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0567. Min Act: -0.0003

Data Index: 382378 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0554. Min Act: -0.0004

Data Index: 379682 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0558. Min Act: -0.0003

Data Index: 365009 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0560. Min Act: -0.0003

Data Index: 913371 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0551. Min Act: -0.0003

Data Index: 1038869 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0550. Min Act: -0.0004

Data Index: 938670 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0536. Min Act: -0.0003

Data Index: 325195 (C4 (Web Text))

Max Activating Token Index: 153