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

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

Neuron 2193 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0278. Min Range: -1.0278

Max Act: 1.0072. Min Act: -0.0003

Data Index: 1004943 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.0278. Min Range: -1.0278

Max Act: 1.0278. Min Act: -0.0003

Data Index: 1226897 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.9971. Min Act: -0.0003

Data Index: 985803 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.9191. Min Act: -0.0003

Data Index: 382669 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.9742. Min Act: -0.0003

Data Index: 263903 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8792. Min Act: -0.0002

Data Index: 1637 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8681. Min Act: -0.0003

Data Index: 243322 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8612. Min Act: -0.0003

Data Index: 1272856 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8364. Min Act: -0.0003

Data Index: 545634 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8039. Min Act: -0.0002

Data Index: 476139 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8277. Min Act: -0.0003

Data Index: 792910 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7677. Min Act: -0.0003

Data Index: 47715 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8163. Min Act: -0.0003

Data Index: 526687 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8143. Min Act: -0.0003

Data Index: 76306 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7738. Min Act: -0.0003

Data Index: 1275422 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7719. Min Act: -0.0003

Data Index: 921027 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7418. Min Act: -0.0003

Data Index: 1193309 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8150. Min Act: -0.0002

Data Index: 681677 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7829. Min Act: -0.0003

Data Index: 369309 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7750. Min Act: -0.0003

Data Index: 513694 (C4 (Web Text))

Max Activating Token Index: 558