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

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

Neuron 5983 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8984. Min Act: -0.0000

Data Index: 563405 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.1480. Min Act: -0.0000

Data Index: 678360 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.1283. Min Act: -0.0000

Data Index: 513838 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.0705. Min Act: -0.0000

Data Index: 1320081 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.0602. Min Act: -0.0000

Data Index: 210503 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.0538. Min Act: -0.0000

Data Index: 228314 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.0234. Min Act: -0.0000

Data Index: 1005077 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.0223. Min Act: -0.0000

Data Index: 552800 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.8802. Min Act: -0.0000

Data Index: 732412 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.9833. Min Act: -0.0000

Data Index: 1497380 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.9844. Min Act: -0.0000

Data Index: 1257183 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.9435. Min Act: -0.0000

Data Index: 775952 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.9556. Min Act: -0.0000

Data Index: 921902 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.8043. Min Act: -0.0000

Data Index: 51881 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.0190. Min Act: -0.0000

Data Index: 1112598 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.8974. Min Act: -0.0000

Data Index: 334672 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.8948. Min Act: -0.0000

Data Index: 601266 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.7532. Min Act: -0.0000

Data Index: 682105 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.8926. Min Act: -0.0000

Data Index: 125823 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 2.8984. Min Range: -2.8984

Max Act: 1.9725. Min Act: -0.0000

Data Index: 733738 (C4 (Web Text))

Max Activating Token Index: 180