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

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

Neuron 4317 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8693. Min Act: -0.0000

Data Index: 133694 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1278720 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8236. Min Act: -0.0000

Data Index: 118712 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6801. Min Act: -0.0000

Data Index: 572480 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6558. Min Act: -0.0000

Data Index: 602122 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6129. Min Act: -0.0000

Data Index: 682714 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.5819. Min Act: -0.0000

Data Index: 771738 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.5717. Min Act: -0.0000

Data Index: 171431 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1282270 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.5233. Min Act: -0.0000

Data Index: 789957 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.4856. Min Act: -0.0000

Data Index: 282406 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1241196 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1391153 (Python Code)

Max Activating Token Index: 203

Text #13

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1295243 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.4246. Min Act: -0.0000

Data Index: 111364 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1197392 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.4586. Min Act: -0.0000

Data Index: 950956 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1245982 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1356240 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1019385 (C4 (Web Text))

Max Activating Token Index: 290