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

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

Neuron 5025 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: 1.3656. Min Range: -1.3656

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1259754 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.3656. Min Act: -0.0000

Data Index: 635300 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.2245. Min Act: -0.0000

Data Index: 1006095 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.2548. Min Act: -0.0000

Data Index: 869808 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.0028. Min Act: -0.0000

Data Index: 39197 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.1180. Min Act: -0.0000

Data Index: 1129739 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.1775. Min Act: -0.0000

Data Index: 839766 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.0485. Min Act: -0.0000

Data Index: 79573 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.1143. Min Act: -0.0000

Data Index: 487904 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.0753. Min Act: -0.0000

Data Index: 713283 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.0909. Min Act: -0.0000

Data Index: 191576 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1116941 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1111952 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.3656. Min Range: -1.3656

Max Act: 1.0576. Min Act: -0.0000

Data Index: 219105 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.3656. Min Range: -1.3656

Max Act: 0.8608. Min Act: -0.0000

Data Index: 914959 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.3656. Min Range: -1.3656

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1081965 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 1.3656. Min Range: -1.3656

Max Act: 0.9361. Min Act: -0.0000

Data Index: 205213 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 1.3656. Min Range: -1.3656

Max Act: 0.8108. Min Act: -0.0000

Data Index: 865230 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.3656. Min Range: -1.3656

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1303057 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 1.3656. Min Range: -1.3656

Max Act: 0.8225. Min Act: -0.0000

Data Index: 692451 (C4 (Web Text))

Max Activating Token Index: 366