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

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

Neuron 908 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.3006. Min Act: -0.0002

Data Index: 771225 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2776. Min Act: -0.0002

Data Index: 100913 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2486. Min Act: -0.0002

Data Index: 256384 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2279. Min Act: -0.0002

Data Index: 8956 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2273. Min Act: -0.0002

Data Index: 795490 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2294. Min Act: -0.0002

Data Index: 66645 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2181. Min Act: -0.0002

Data Index: 842773 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2175. Min Act: -0.0002

Data Index: 362130 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2107. Min Act: -0.0002

Data Index: 244628 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2163. Min Act: -0.0002

Data Index: 1146277 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2123. Min Act: -0.0002

Data Index: 739239 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2191. Min Act: -0.0002

Data Index: 346081 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.1999. Min Act: -0.0002

Data Index: 306144 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2024. Min Act: -0.0002

Data Index: 388721 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.1968. Min Act: -0.0002

Data Index: 841226 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.1910. Min Act: -0.0002

Data Index: 1352560 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.2066. Min Act: -0.0002

Data Index: 628427 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.1987. Min Act: -0.0002

Data Index: 941351 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.1991. Min Act: -0.0002

Data Index: 132379 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.3006. Min Range: -0.3006

Max Act: 0.1981. Min Act: -0.0002

Data Index: 126163 (C4 (Web Text))

Max Activating Token Index: 307