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

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

Neuron 4334 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.9710. Min Act: -0.0000

Data Index: 489712 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 1.0342. Min Range: -1.0342

Max Act: 1.0236. Min Act: -0.0000

Data Index: 1058882 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 1.0342. Min Range: -1.0342

Max Act: 1.0043. Min Act: -0.0000

Data Index: 23972 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.9404. Min Act: -0.0000

Data Index: 236762 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.9848. Min Act: -0.0000

Data Index: 79525 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 1.0342. Min Range: -1.0342

Max Act: 1.0342. Min Act: -0.0000

Data Index: 238292 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.9823. Min Act: -0.0000

Data Index: 628561 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.9243. Min Act: -0.0000

Data Index: 477930 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.8685. Min Act: -0.0000

Data Index: 996247 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1226197 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.0342. Min Range: -1.0342

Max Act: 1.0228. Min Act: -0.0000

Data Index: 352931 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.9212. Min Act: -0.0000

Data Index: 971233 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1056273 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.9328. Min Act: -0.0000

Data Index: 15764 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.8439. Min Act: -0.0000

Data Index: 43364 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.8607. Min Act: -0.0000

Data Index: 364903 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.7361. Min Act: -0.0000

Data Index: 808087 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.7395. Min Act: -0.0000

Data Index: 35850 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6881. Min Act: -0.0000

Data Index: 178559 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 1.0342. Min Range: -1.0342

Max Act: 0.6765. Min Act: -0.0000

Data Index: 952493 (C4 (Web Text))

Max Activating Token Index: 764