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

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

Neuron 2358 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: 0.9299. Min Range: -0.9299

Max Act: 0.9299. Min Act: -0.0000

Data Index: 143923 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8651. Min Act: -0.0000

Data Index: 720175 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8539. Min Act: -0.0000

Data Index: 284793 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8492. Min Act: -0.0000

Data Index: 63001 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8503. Min Act: -0.0000

Data Index: 984765 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7730. Min Act: -0.0000

Data Index: 494598 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1325458 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1194511 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8040. Min Act: -0.0000

Data Index: 664926 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1046183 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7997. Min Act: -0.0000

Data Index: 58041 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7548. Min Act: -0.0000

Data Index: 282375 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1224916 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1356412 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7300. Min Act: -0.0000

Data Index: 160400 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7014. Min Act: -0.0000

Data Index: 494109 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7540. Min Act: -0.0000

Data Index: 764467 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7372. Min Act: -0.0000

Data Index: 867349 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7379. Min Act: -0.0000

Data Index: 27449 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7154. Min Act: -0.0000

Data Index: 265438 (C4 (Web Text))

Max Activating Token Index: 18