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

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

Neuron 4345 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2277. Min Range: -5.2277

Max Act: 5.1324. Min Act: -0.0000

Data Index: 536312 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 5.2277. Min Range: -5.2277

Max Act: 5.2277. Min Act: -0.0000

Data Index: 402656 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.7987. Min Act: -0.0000

Data Index: 579528 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.8337. Min Act: -0.0000

Data Index: 436497 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.5590. Min Act: -0.0000

Data Index: 1062317 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.5599. Min Act: -0.0000

Data Index: 373968 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.3674. Min Act: -0.0000

Data Index: 722617 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.2366. Min Act: -0.0000

Data Index: 277904 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.0629. Min Act: -0.0000

Data Index: 570125 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.0208. Min Act: -0.0000

Data Index: 1276764 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.1697. Min Act: -0.0000

Data Index: 1199840 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.1054. Min Act: -0.0000

Data Index: 207461 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.0488. Min Act: -0.0000

Data Index: 1162236 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.0540. Min Act: -0.0000

Data Index: 123483 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.0015. Min Act: -0.0000

Data Index: 400292 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 5.2277. Min Range: -5.2277

Max Act: 3.9868. Min Act: -0.0000

Data Index: 552122 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.1239. Min Act: -0.0000

Data Index: 1113873 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.2535. Min Act: -0.0000

Data Index: 313592 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 5.2277. Min Range: -5.2277

Max Act: 4.0866. Min Act: -0.0000

Data Index: 432384 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 5.2277. Min Range: -5.2277

Max Act: 3.6968. Min Act: -0.0000

Data Index: 389109 (C4 (Web Text))

Max Activating Token Index: 790