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

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

Neuron 3228 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: 1.2221. Min Range: -1.2221

Max Act: 1.1847. Min Act: -0.0000

Data Index: 523376 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.1313. Min Act: -0.0000

Data Index: 386439 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1353578 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.2221. Min Act: -0.0000

Data Index: 156084 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.1092. Min Act: -0.0000

Data Index: 758064 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.1012. Min Act: -0.0000

Data Index: 660580 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.0909. Min Act: -0.0000

Data Index: 171571 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1034398 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.0144. Min Act: -0.0000

Data Index: 784729 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.0428. Min Act: -0.0000

Data Index: 972191 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.1002. Min Act: -0.0000

Data Index: 422332 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.0186. Min Act: -0.0000

Data Index: 948967 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1140480 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9504. Min Act: -0.0000

Data Index: 16072 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9119. Min Act: -0.0000

Data Index: 359973 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8884. Min Act: -0.0000

Data Index: 58241 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8487. Min Act: -0.0000

Data Index: 851242 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9174. Min Act: -0.0000

Data Index: 821856 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8623. Min Act: -0.0000

Data Index: 689809 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9072. Min Act: -0.0000

Data Index: 305057 (C4 (Web Text))

Max Activating Token Index: 911