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

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

Neuron 2428 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1263098 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.6896. Min Act: -0.0000

Data Index: 72407 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.5890. Min Act: -0.0000

Data Index: 416789 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.7455. Min Act: -0.0000

Data Index: 487805 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.5114. Min Act: -0.0000

Data Index: 974020 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.3865. Min Act: -0.0000

Data Index: 1196905 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.5142. Min Act: -0.0000

Data Index: 1254521 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.5153. Min Act: -0.0000

Data Index: 226387 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.4630. Min Act: -0.0000

Data Index: 151723 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.5209. Min Act: -0.0000

Data Index: 1322271 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.4257. Min Act: -0.0000

Data Index: 881417 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.3332. Min Act: -0.0000

Data Index: 1158206 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.4403. Min Act: -0.0000

Data Index: 513531 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.4220. Min Act: -0.0000

Data Index: 32158 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.2353. Min Act: -0.0000

Data Index: 170151 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.2187. Min Act: -0.0000

Data Index: 819903 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.2141. Min Act: -0.0000

Data Index: 182348 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.3216. Min Act: -0.0000

Data Index: 292877 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.3073. Min Act: -0.0000

Data Index: 284583 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 1.7455. Min Range: -1.7455

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1314657 (C4 (Web Text))

Max Activating Token Index: 987