Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1731 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3115. Min Act: -0.0000

Data Index: 884582 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2704. Min Act: -0.0000

Data Index: 413375 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1012235 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2399. Min Act: -0.0000

Data Index: 458465 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2318. Min Act: -0.0000

Data Index: 623471 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2202. Min Act: -0.0000

Data Index: 919167 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.1984. Min Act: -0.0000

Data Index: 695866 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2210. Min Act: -0.0000

Data Index: 374095 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2186. Min Act: -0.0000

Data Index: 411191 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2104. Min Act: -0.0000

Data Index: 507890 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1131108 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2032. Min Act: -0.0000

Data Index: 130510 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.1985. Min Act: -0.0000

Data Index: 808716 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2036. Min Act: -0.0000

Data Index: 327924 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2034. Min Act: -0.0000

Data Index: 483170 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2023. Min Act: -0.0000

Data Index: 665000 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.1999. Min Act: -0.0000

Data Index: 613031 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1187189 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2020. Min Act: -0.0000

Data Index: 35042 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.1942. Min Act: -0.0000

Data Index: 668757 (C4 (Web Text))

Max Activating Token Index: 879