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

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

Neuron 988 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.7295. Min Act: -0.0001

Data Index: 725661 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1122491 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5932. Min Act: -0.0001

Data Index: 1081187 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5400. Min Act: -0.0001

Data Index: 731712 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5240. Min Act: -0.0000

Data Index: 851611 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5396. Min Act: -0.0001

Data Index: 1131329 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4970. Min Act: -0.0000

Data Index: 38980 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1313589 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5031. Min Act: -0.0000

Data Index: 339342 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5168. Min Act: -0.0001

Data Index: 884711 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4985. Min Act: -0.0000

Data Index: 313199 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4868. Min Act: -0.0000

Data Index: 157425 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1110381 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4792. Min Act: -0.0001

Data Index: 524015 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4789. Min Act: -0.0000

Data Index: 884199 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4791. Min Act: -0.0000

Data Index: 534024 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4769. Min Act: -0.0001

Data Index: 1110345 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4711. Min Act: -0.0001

Data Index: 311330 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4883. Min Act: -0.0001

Data Index: 6783 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4565. Min Act: -0.0000

Data Index: 124604 (C4 (Web Text))

Max Activating Token Index: 299