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

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

Neuron 207 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.7604. Min Act: -0.0000

Data Index: 547113 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.6601. Min Act: -0.0000

Data Index: 529824 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.6083. Min Act: -0.0000

Data Index: 89317 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.5948. Min Act: -0.0000

Data Index: 1314427 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.6006. Min Act: -0.0000

Data Index: 733881 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1273178 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1354734 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1022399 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.4781. Min Act: -0.0000

Data Index: 394285 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.4589. Min Act: -0.0000

Data Index: 979537 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.4245. Min Act: -0.0000

Data Index: 584228 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.4097. Min Act: -0.0000

Data Index: 580050 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.3291. Min Act: -0.0000

Data Index: 329186 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.3022. Min Act: -0.0000

Data Index: 383603 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.3751. Min Act: 0.0000

Data Index: 71843 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.3528. Min Act: -0.0000

Data Index: 964191 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.3451. Min Act: -0.0000

Data Index: 1192578 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1255040 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.3245. Min Act: -0.0000

Data Index: 416737 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 1.7604. Min Range: -1.7604

Max Act: 1.2547. Min Act: -0.0000

Data Index: 135644 (C4 (Web Text))

Max Activating Token Index: 993