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

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

Neuron 226 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.7305. Min Act: -0.0000

Data Index: 121890 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.5672. Min Act: -0.0000

Data Index: 738470 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.7371. Min Act: -0.0000

Data Index: 845153 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.2984. Min Act: -0.0000

Data Index: 826274 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.4039. Min Act: -0.0000

Data Index: 291961 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.4003. Min Act: -0.0000

Data Index: 650885 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.3192. Min Act: -0.0000

Data Index: 329544 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.3497. Min Act: -0.0000

Data Index: 81246 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.2587. Min Act: -0.0000

Data Index: 664469 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1231446 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.2074. Min Act: -0.0000

Data Index: 1335177 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.1896. Min Act: -0.0000

Data Index: 632784 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1280631 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.1244. Min Act: -0.0000

Data Index: 34144 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.0362. Min Act: -0.0000

Data Index: 304978 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1336100 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1028225 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 1.7371. Min Range: -1.7371

Max Act: 0.9713. Min Act: -0.0000

Data Index: 774816 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 1.7371. Min Range: -1.7371

Max Act: 0.9850. Min Act: -0.0000

Data Index: 563544 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.7371. Min Range: -1.7371

Max Act: 1.0094. Min Act: -0.0000

Data Index: 574822 (C4 (Web Text))

Max Activating Token Index: 487