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

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

Neuron 2756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7059. Min Range: -6.7059

Max Act: 6.7059. Min Act: -0.0000

Data Index: 91878 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 6.7059. Min Range: -6.7059

Max Act: 6.2450. Min Act: -0.0000

Data Index: 1285436 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 6.7059. Min Range: -6.7059

Max Act: 5.2568. Min Act: -0.0000

Data Index: 607002 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 6.7059. Min Range: -6.7059

Max Act: 5.5080. Min Act: -0.0000

Data Index: 828523 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 6.7059. Min Range: -6.7059

Max Act: 5.5770. Min Act: -0.0000

Data Index: 766583 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.9976. Min Act: -0.0000

Data Index: 365537 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 6.7059. Min Range: -6.7059

Max Act: 5.1649. Min Act: -0.0000

Data Index: 536333 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 6.7059. Min Range: -6.7059

Max Act: 5.1699. Min Act: -0.0000

Data Index: 652882 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 6.7059. Min Range: -6.7059

Max Act: 5.3535. Min Act: -0.0000

Data Index: 76903 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.8772. Min Act: -0.0000

Data Index: 1316816 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.2317. Min Act: -0.0000

Data Index: 831832 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.8564. Min Act: -0.0000

Data Index: 643788 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 6.7059. Min Range: -6.7059

Max Act: 5.3407. Min Act: -0.0000

Data Index: 604716 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.5636. Min Act: -0.0000

Data Index: 1169446 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.6595. Min Act: -0.0000

Data Index: 1317150 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.9016. Min Act: -0.0000

Data Index: 540305 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.3054. Min Act: -0.0000

Data Index: 147461 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.5246. Min Act: -0.0000

Data Index: 52227 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.8000. Min Act: -0.0000

Data Index: 651062 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 6.7059. Min Range: -6.7059

Max Act: 4.9525. Min Act: -0.0000

Data Index: 346551 (C4 (Web Text))

Max Activating Token Index: 89