Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4023 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1925. Min Act: -0.0003

Data Index: 213391 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1185. Min Act: -0.0003

Data Index: 476132 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1184. Min Act: -0.0003

Data Index: 86209 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1105. Min Act: -0.0003

Data Index: 730935 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0948. Min Act: -0.0003

Data Index: 982112 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0753. Min Act: -0.0003

Data Index: 960897 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0744. Min Act: -0.0002

Data Index: 686194 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0598. Min Act: -0.0003

Data Index: 873932 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0298. Min Act: -0.0003

Data Index: 910057 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0174. Min Act: -0.0003

Data Index: 906152 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0135. Min Act: -0.0003

Data Index: 76117 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0113. Min Act: -0.0003

Data Index: 640132 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0095. Min Act: -0.0003

Data Index: 1259046 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0082. Min Act: -0.0002

Data Index: 965245 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0062. Min Act: -0.0003

Data Index: 974734 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0055. Min Act: -0.0003

Data Index: 946428 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0033. Min Act: -0.0003

Data Index: 27890 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0012. Min Act: -0.0003

Data Index: 1265526 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9997. Min Act: -0.0003

Data Index: 273516 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9982. Min Act: -0.0002

Data Index: 910785 (C4 (Web Text))

Max Activating Token Index: 239