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

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

Neuron 4310 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: 1.0096. Min Range: -1.0096

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1284843 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.9216. Min Act: -0.0000

Data Index: 602480 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8637. Min Act: -0.0000

Data Index: 620736 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8625. Min Act: -0.0000

Data Index: 211605 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8427. Min Act: -0.0000

Data Index: 62307 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8159. Min Act: -0.0000

Data Index: 29432 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.8025. Min Act: -0.0000

Data Index: 644803 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7963. Min Act: -0.0000

Data Index: 253096 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7493. Min Act: -0.0000

Data Index: 466446 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7082. Min Act: -0.0000

Data Index: 847026 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7287. Min Act: -0.0000

Data Index: 47936 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7297. Min Act: -0.0000

Data Index: 468867 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7144. Min Act: -0.0000

Data Index: 938706 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7116. Min Act: -0.0000

Data Index: 901208 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7196. Min Act: -0.0000

Data Index: 604252 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7037. Min Act: -0.0000

Data Index: 416073 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1135039 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.7020. Min Act: -0.0000

Data Index: 636576 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6475. Min Act: -0.0000

Data Index: 391778 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 1.0096. Min Range: -1.0096

Max Act: 0.6421. Min Act: -0.0000

Data Index: 579815 (C4 (Web Text))

Max Activating Token Index: 17