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

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

Neuron 3494 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0623. Min Range: -1.0623

Max Act: 1.0623. Min Act: -0.0000

Data Index: 367450 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.8328. Min Act: -0.0000

Data Index: 280294 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1260411 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1311992 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.7787. Min Act: -0.0000

Data Index: 72689 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1066931 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.8016. Min Act: -0.0000

Data Index: 559029 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1266476 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1075750 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1001026 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1269392 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6945. Min Act: -0.0000

Data Index: 999836 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.7338. Min Act: -0.0000

Data Index: 867848 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.7492. Min Act: -0.0000

Data Index: 278153 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6569. Min Act: -0.0000

Data Index: 60268 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6776. Min Act: -0.0000

Data Index: 422122 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6553. Min Act: -0.0000

Data Index: 622218 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1167173 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6257. Min Act: -0.0000

Data Index: 515745 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6337. Min Act: -0.0000

Data Index: 486974 (C4 (Web Text))

Max Activating Token Index: 70