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

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

Neuron 3879 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.9414. Min Act: -0.0000

Data Index: 931815 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.5783. Min Act: -0.0000

Data Index: 426358 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.3750. Min Act: -0.0000

Data Index: 1027382 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.3620. Min Act: -0.0000

Data Index: 85631 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.1906. Min Act: -0.0000

Data Index: 278335 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.2291. Min Act: -0.0000

Data Index: 1081949 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.2948. Min Act: -0.0000

Data Index: 449272 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.1502. Min Act: -0.0000

Data Index: 1264135 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.0253. Min Act: -0.0000

Data Index: 784448 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.9921. Min Act: -0.0000

Data Index: 914110 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.0857. Min Act: -0.0000

Data Index: 795741 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.9664. Min Act: -0.0000

Data Index: 282776 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.9563. Min Act: -0.0000

Data Index: 806421 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.0359. Min Act: -0.0000

Data Index: 131389 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.9323. Min Act: -0.0000

Data Index: 546794 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 2.9414. Min Range: -2.9414

Max Act: 2.0760. Min Act: -0.0000

Data Index: 90865 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.8187. Min Act: -0.0000

Data Index: 688105 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.8120. Min Act: -0.0000

Data Index: 266305 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.9228. Min Act: -0.0000

Data Index: 1060698 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 2.9414. Min Range: -2.9414

Max Act: 1.7814. Min Act: -0.0000

Data Index: 957124 (C4 (Web Text))

Max Activating Token Index: 82