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

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

Neuron 4931 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: 0.2855. Min Range: -0.2855

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1006511 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2855. Min Act: -0.0000

Data Index: 289626 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2660. Min Act: -0.0000

Data Index: 314128 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1299548 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2568. Min Act: -0.0000

Data Index: 478567 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1224868 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2629. Min Act: -0.0000

Data Index: 804067 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2387. Min Act: -0.0000

Data Index: 800151 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2281. Min Act: -0.0000

Data Index: 304192 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2199. Min Act: -0.0000

Data Index: 674740 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1044663 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2174. Min Act: -0.0000

Data Index: 338129 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2290. Min Act: -0.0000

Data Index: 165878 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1961. Min Act: -0.0000

Data Index: 475418 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1057230 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2163. Min Act: -0.0000

Data Index: 298435 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1192374 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2084. Min Act: -0.0000

Data Index: 56074 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2191. Min Act: -0.0000

Data Index: 831544 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.2855. Min Range: -0.2855

Max Act: 0.2043. Min Act: -0.0000

Data Index: 540207 (C4 (Web Text))

Max Activating Token Index: 687