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

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

Neuron 4876 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: 0.7254. Min Range: -0.7254

Max Act: 0.7254. Min Act: 0.0000

Data Index: 41727 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.6443. Min Act: -0.0000

Data Index: 684394 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.5733. Min Act: -0.0000

Data Index: 288668 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.5757. Min Act: -0.0000

Data Index: 771749 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.5717. Min Act: -0.0000

Data Index: 328186 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.5084. Min Act: -0.0000

Data Index: 309387 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.4736. Min Act: -0.0000

Data Index: 904940 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.4482. Min Act: -0.0000

Data Index: 979871 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1336648 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3718. Min Act: -0.0000

Data Index: 799164 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3712. Min Act: -0.0000

Data Index: 687569 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3654. Min Act: -0.0000

Data Index: 924427 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1000903 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3455. Min Act: -0.0000

Data Index: 365327 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3551. Min Act: -0.0000

Data Index: 437758 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1142624 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3459. Min Act: -0.0000

Data Index: 141851 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3436. Min Act: -0.0000

Data Index: 382173 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3308. Min Act: -0.0000

Data Index: 430322 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.7254. Min Range: -0.7254

Max Act: 0.3404. Min Act: -0.0000

Data Index: 287184 (C4 (Web Text))

Max Activating Token Index: 859