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

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

Neuron 4244 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.7959. Min Act: -0.0000

Data Index: 180189 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1116391 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.6677. Min Act: -0.0000

Data Index: 474351 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.6724. Min Act: -0.0000

Data Index: 186861 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1303528 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.6344. Min Act: -0.0000

Data Index: 195986 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1175634 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.6127. Min Act: -0.0000

Data Index: 765779 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.5893. Min Act: -0.0000

Data Index: 466089 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1066697 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1467868 (Python Code)

Max Activating Token Index: 136

Text #11

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.5444. Min Act: -0.0000

Data Index: 849475 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.4860. Min Act: -0.0000

Data Index: 932206 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1298125 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.5266. Min Act: -0.0000

Data Index: 75738 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.5033. Min Act: -0.0000

Data Index: 358008 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.4820. Min Act: -0.0000

Data Index: 11747 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.5291. Min Act: -0.0000

Data Index: 36975 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1230612 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.7959. Min Range: -0.7959

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1013524 (C4 (Web Text))

Max Activating Token Index: 441