Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4287 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.1987. Min Act: -0.0000

Data Index: 1313172 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1071878 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.2208. Min Act: -0.0000

Data Index: 731726 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.1210. Min Act: -0.0000

Data Index: 16969 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.0327. Min Act: -0.0000

Data Index: 580328 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9315. Min Act: -0.0000

Data Index: 521923 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.0749. Min Act: -0.0000

Data Index: 820561 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9494. Min Act: -0.0000

Data Index: 578293 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8824. Min Act: -0.0000

Data Index: 647 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1069086 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9771. Min Act: -0.0000

Data Index: 684073 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8753. Min Act: -0.0000

Data Index: 43804 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1191573 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8650. Min Act: -0.0000

Data Index: 359634 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8742. Min Act: -0.0000

Data Index: 44554 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8831. Min Act: -0.0000

Data Index: 263546 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8821. Min Act: -0.0000

Data Index: 236643 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9970. Min Act: -0.0000

Data Index: 466423 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1009461 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9039. Min Act: -0.0000

Data Index: 701101 (C4 (Web Text))

Max Activating Token Index: 551