Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3959 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1183. Min Act: -0.0002

Data Index: 587085 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1094. Min Act: -0.0002

Data Index: 330161 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1047. Min Act: -0.0002

Data Index: 703608 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1073. Min Act: -0.0002

Data Index: 865586 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0924. Min Act: -0.0002

Data Index: 443190 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1287025 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1025090 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0977. Min Act: -0.0002

Data Index: 925420 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1178156 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0987. Min Act: -0.0002

Data Index: 846846 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0931. Min Act: -0.0002

Data Index: 791691 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1064979 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1136503 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1249137 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1042782 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0790. Min Act: -0.0002

Data Index: 620983 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1023. Min Act: -0.0002

Data Index: 483313 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0911. Min Act: -0.0002

Data Index: 313766 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1022865 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0924. Min Act: -0.0002

Data Index: 399389 (C4 (Web Text))

Max Activating Token Index: 518