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

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

Neuron 715 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: 0.6627. Min Range: -0.6627

Max Act: 0.6627. Min Act: -0.0000

Data Index: 17915 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1080892 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.6510. Min Act: -0.0000

Data Index: 33523 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5810. Min Act: -0.0000

Data Index: 329285 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5723. Min Act: -0.0000

Data Index: 367440 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5711. Min Act: -0.0000

Data Index: 508126 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5835. Min Act: -0.0000

Data Index: 461142 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5497. Min Act: -0.0000

Data Index: 100065 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1133518 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5129. Min Act: -0.0000

Data Index: 280891 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4872. Min Act: -0.0000

Data Index: 273432 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5169. Min Act: -0.0000

Data Index: 618849 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1235504 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5277. Min Act: -0.0000

Data Index: 214316 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5187. Min Act: -0.0000

Data Index: 353172 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1063185 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1056154 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1010528 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4933. Min Act: -0.0000

Data Index: 872095 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.5182. Min Act: -0.0000

Data Index: 878113 (C4 (Web Text))

Max Activating Token Index: 980