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

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

Neuron 3511 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: 1.4419. Min Range: -1.4419

Max Act: 1.4419. Min Act: -0.0003

Data Index: 908771 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3998. Min Act: -0.0003

Data Index: 9803 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.4301. Min Act: -0.0003

Data Index: 745762 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.3350. Min Act: -0.0003

Data Index: 33929 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.2929. Min Act: -0.0003

Data Index: 1298607 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.2801. Min Act: -0.0003

Data Index: 1026184 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.1662. Min Act: -0.0003

Data Index: 258055 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.1220. Min Act: -0.0003

Data Index: 223198 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.0854. Min Act: -0.0003

Data Index: 788727 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.0537. Min Act: -0.0003

Data Index: 1216535 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.0488. Min Act: -0.0003

Data Index: 744746 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.0095. Min Act: -0.0003

Data Index: 764109 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.0163. Min Act: -0.0003

Data Index: 381652 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.4419. Min Range: -1.4419

Max Act: 1.0074. Min Act: -0.0003

Data Index: 735774 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9688. Min Act: -0.0003

Data Index: 1292334 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9708. Min Act: -0.0003

Data Index: 644646 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9751. Min Act: -0.0002

Data Index: 1353882 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9514. Min Act: -0.0002

Data Index: 836098 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9581. Min Act: -0.0003

Data Index: 1337898 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 1.4419. Min Range: -1.4419

Max Act: 0.9595. Min Act: -0.0003

Data Index: 4021 (C4 (Web Text))

Max Activating Token Index: 262