Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 56 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3196. Min Range: -3.3196

Max Act: 3.3196. Min Act: -0.0000

Data Index: 466260 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.4786. Min Act: -0.0000

Data Index: 353160 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.5354. Min Act: -0.0000

Data Index: 1050236 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.4169. Min Act: -0.0000

Data Index: 1237592 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.4875. Min Act: -0.0000

Data Index: 1210613 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.3887. Min Act: -0.0000

Data Index: 1196013 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.4978. Min Act: -0.0000

Data Index: 671941 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.1531. Min Act: -0.0000

Data Index: 641749 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.3776. Min Act: -0.0000

Data Index: 1342191 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.1213. Min Act: -0.0000

Data Index: 1101277 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.0789. Min Act: -0.0000

Data Index: 362454 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.1721. Min Act: -0.0000

Data Index: 159484 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.1672. Min Act: -0.0000

Data Index: 95765 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.0626. Min Act: -0.0000

Data Index: 64320 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.0480. Min Act: -0.0000

Data Index: 689552 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.1383. Min Act: -0.0000

Data Index: 676687 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.1313. Min Act: -0.0000

Data Index: 1004365 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.0151. Min Act: -0.0000

Data Index: 257096 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.1039. Min Act: -0.0000

Data Index: 1166555 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 3.3196. Min Range: -3.3196

Max Act: 2.1100. Min Act: -0.0000

Data Index: 731226 (C4 (Web Text))

Max Activating Token Index: 267