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

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

Neuron 43 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1035225 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.8327. Min Act: -0.0000

Data Index: 424087 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.8254. Min Act: -0.0000

Data Index: 302798 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7948. Min Act: -0.0000

Data Index: 316241 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.8102. Min Act: -0.0000

Data Index: 197602 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.8876. Min Act: -0.0000

Data Index: 392717 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7642. Min Act: -0.0000

Data Index: 468594 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7584. Min Act: -0.0000

Data Index: 561142 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1144482 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7695. Min Act: -0.0000

Data Index: 24781 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1343149 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7585. Min Act: -0.0000

Data Index: 177703 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7620. Min Act: -0.0000

Data Index: 339275 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1294316 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7308. Min Act: -0.0000

Data Index: 689982 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7340. Min Act: -0.0000

Data Index: 819640 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7391. Min Act: -0.0000

Data Index: 173833 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1432051 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7100. Min Act: -0.0000

Data Index: 401818 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7114. Min Act: -0.0000

Data Index: 906646 (C4 (Web Text))

Max Activating Token Index: 919