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

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

Neuron 5705 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0689. Min Act: -0.0002

Data Index: 730001 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1115621 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0459. Min Act: -0.0002

Data Index: 608602 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0374. Min Act: -0.0002

Data Index: 516194 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1115119 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0366. Min Act: -0.0002

Data Index: 802580 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0344. Min Act: -0.0002

Data Index: 340686 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0340. Min Act: -0.0002

Data Index: 907554 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1348924 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0335. Min Act: -0.0002

Data Index: 45645 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0332. Min Act: -0.0002

Data Index: 4744 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1083064 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1189341 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0321. Min Act: -0.0002

Data Index: 351115 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0323. Min Act: -0.0002

Data Index: 498185 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0320. Min Act: -0.0002

Data Index: 649324 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1250991 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0311. Min Act: -0.0002

Data Index: 380943 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0316. Min Act: -0.0002

Data Index: 623309 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0314. Min Act: -0.0002

Data Index: 548256 (C4 (Web Text))

Max Activating Token Index: 228