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

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

Neuron 2924 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.8183. Min Act: -0.0000

Data Index: 751244 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.5959. Min Act: -0.0000

Data Index: 1263058 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.1882. Min Act: -0.0000

Data Index: 338739 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.3741. Min Act: -0.0000

Data Index: 90967 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.5153. Min Act: -0.0000

Data Index: 75525 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.2038. Min Act: -0.0000

Data Index: 582098 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.2878. Min Act: -0.0000

Data Index: 66626 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.2869. Min Act: -0.0001

Data Index: 140270 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1074018 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.4083. Min Act: -0.0000

Data Index: 829008 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.1196. Min Act: -0.0000

Data Index: 1125816 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.0890. Min Act: -0.0000

Data Index: 930277 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.1469. Min Act: -0.0000

Data Index: 264005 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.0992. Min Act: -0.0000

Data Index: 887191 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.2219. Min Act: -0.0000

Data Index: 126282 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.1686. Min Act: -0.0000

Data Index: 1253784 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1069754 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.0744. Min Act: -0.0000

Data Index: 404359 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.1226. Min Act: -0.0000

Data Index: 164612 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 1.8183. Min Range: -1.8183

Max Act: 1.1743. Min Act: -0.0000

Data Index: 118378 (C4 (Web Text))

Max Activating Token Index: 455