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

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

Neuron 4784 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1079069 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6418. Min Act: -0.0000

Data Index: 870026 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6849. Min Act: -0.0000

Data Index: 575725 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6783. Min Act: -0.0000

Data Index: 705400 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6631. Min Act: -0.0000

Data Index: 998457 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5507. Min Act: -0.0000

Data Index: 686743 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5312. Min Act: -0.0000

Data Index: 76258 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5412. Min Act: -0.0000

Data Index: 783932 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5826. Min Act: -0.0000

Data Index: 936126 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5405. Min Act: -0.0000

Data Index: 35882 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5217. Min Act: -0.0000

Data Index: 166891 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5076. Min Act: -0.0000

Data Index: 570778 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4851. Min Act: -0.0000

Data Index: 383810 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4626. Min Act: -0.0000

Data Index: 776940 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4612. Min Act: -0.0000

Data Index: 481915 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4469. Min Act: -0.0000

Data Index: 788560 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1322241 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4554. Min Act: -0.0000

Data Index: 279201 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4482. Min Act: -0.0000

Data Index: 718875 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1335835 (C4 (Web Text))

Max Activating Token Index: 15