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

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

Neuron 2048 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: 2.4854. Min Range: -2.4854

Max Act: 2.4854. Min Act: -0.0000

Data Index: 475446 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.4718. Min Act: -0.0000

Data Index: 478809 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.3747. Min Act: -0.0000

Data Index: 1107629 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.2793. Min Act: -0.0000

Data Index: 470980 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.3734. Min Act: -0.0000

Data Index: 664629 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.2431. Min Act: -0.0000

Data Index: 1064852 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.0367. Min Act: -0.0000

Data Index: 197820 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.1418. Min Act: -0.0000

Data Index: 1222275 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.1285. Min Act: -0.0000

Data Index: 999738 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.0719. Min Act: -0.0000

Data Index: 411051 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.0703. Min Act: -0.0000

Data Index: 1068888 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.0695. Min Act: -0.0000

Data Index: 620876 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.0102. Min Act: -0.0000

Data Index: 328963 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.0160. Min Act: -0.0000

Data Index: 543944 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 2.4854. Min Range: -2.4854

Max Act: 2.0052. Min Act: -0.0000

Data Index: 18776 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 2.4854. Min Range: -2.4854

Max Act: 1.9943. Min Act: -0.0000

Data Index: 36842 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 2.4854. Min Range: -2.4854

Max Act: 1.8824. Min Act: -0.0000

Data Index: 415017 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 2.4854. Min Range: -2.4854

Max Act: 1.8781. Min Act: -0.0000

Data Index: 1235931 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 2.4854. Min Range: -2.4854

Max Act: 1.9461. Min Act: -0.0000

Data Index: 1046836 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 2.4854. Min Range: -2.4854

Max Act: 1.9322. Min Act: -0.0000

Data Index: 1002299 (C4 (Web Text))

Max Activating Token Index: 765