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

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

Neuron 3105 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2596. Min Range: -1.2596

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1328524 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 1.2596. Min Range: -1.2596

Max Act: 1.2174. Min Act: -0.0000

Data Index: 1208410 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 1.2596. Min Range: -1.2596

Max Act: 1.1996. Min Act: -0.0000

Data Index: 357404 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 1.2596. Min Range: -1.2596

Max Act: 1.0676. Min Act: -0.0000

Data Index: 121023 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.2596. Min Range: -1.2596

Max Act: 1.1141. Min Act: -0.0000

Data Index: 913957 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 1.2596. Min Range: -1.2596

Max Act: 1.0920. Min Act: -0.0000

Data Index: 373920 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 1.2596. Min Range: -1.2596

Max Act: 1.1336. Min Act: -0.0000

Data Index: 643268 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 1.2596. Min Range: -1.2596

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1051285 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.9827. Min Act: -0.0000

Data Index: 788240 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.9602. Min Act: -0.0000

Data Index: 853950 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 1.2596. Min Range: -1.2596

Max Act: 1.1345. Min Act: -0.0000

Data Index: 288105 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1228851 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.8877. Min Act: -0.0000

Data Index: 1437636 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1331017 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.8883. Min Act: -0.0000

Data Index: 225449 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.9166. Min Act: -0.0000

Data Index: 719508 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.8753. Min Act: -0.0000

Data Index: 438368 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.8689. Min Act: -0.0000

Data Index: 1325632 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.8664. Min Act: -0.0000

Data Index: 951555 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.2596. Min Range: -1.2596

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1337168 (C4 (Web Text))

Max Activating Token Index: 758