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

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

Neuron 3243 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: 0.5897. Min Range: -0.5897

Max Act: 0.5897. Min Act: -0.0000

Data Index: 584808 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5305. Min Act: -0.0000

Data Index: 329109 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5193. Min Act: -0.0000

Data Index: 170180 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5363. Min Act: -0.0000

Data Index: 380099 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1087626 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.5302. Min Act: -0.0000

Data Index: 63605 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4431. Min Act: -0.0000

Data Index: 886514 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1065617 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4728. Min Act: -0.0000

Data Index: 909024 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1275569 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1183944 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1059005 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4413. Min Act: -0.0000

Data Index: 149172 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4211. Min Act: -0.0000

Data Index: 110974 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1269024 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4416. Min Act: -0.0000

Data Index: 38759 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4268. Min Act: -0.0000

Data Index: 413347 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4467. Min Act: -0.0000

Data Index: 580329 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4005. Min Act: -0.0000

Data Index: 130668 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.5897. Min Range: -0.5897

Max Act: 0.4335. Min Act: -0.0000

Data Index: 229087 (C4 (Web Text))

Max Activating Token Index: 922