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

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

Neuron 1304 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.8589. Min Act: -0.0000

Data Index: 431608 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.8830. Min Act: -0.0000

Data Index: 326342 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.8841. Min Act: -0.0000

Data Index: 903892 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.9238. Min Act: -0.0001

Data Index: 352853 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.8944. Min Act: -0.0000

Data Index: 98358 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.8249. Min Act: -0.0001

Data Index: 355300 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.8278. Min Act: -0.0000

Data Index: 242015 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.8681. Min Act: -0.0001

Data Index: 432916 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7395. Min Act: -0.0000

Data Index: 763171 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7995. Min Act: -0.0000

Data Index: 690477 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7570. Min Act: -0.0000

Data Index: 839529 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7704. Min Act: -0.0000

Data Index: 747979 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7813. Min Act: -0.0000

Data Index: 185511 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1156466 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7370. Min Act: -0.0001

Data Index: 86775 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7342. Min Act: -0.0000

Data Index: 700573 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7476. Min Act: -0.0000

Data Index: 171531 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7216. Min Act: -0.0000

Data Index: 628626 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6567. Min Act: -0.0000

Data Index: 884972 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7067. Min Act: -0.0001

Data Index: 59064 (C4 (Web Text))

Max Activating Token Index: 847