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

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

Neuron 3090 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1189. Min Act: -0.0003

Data Index: 1238525 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1132. Min Act: -0.0002

Data Index: 774515 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1311757 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1294065 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1090. Min Act: -0.0003

Data Index: 919562 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1045. Min Act: -0.0003

Data Index: 691577 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1039. Min Act: -0.0003

Data Index: 215587 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1018. Min Act: -0.0003

Data Index: 985791 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1015. Min Act: -0.0002

Data Index: 185290 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1003. Min Act: -0.0002

Data Index: 982057 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1000. Min Act: -0.0003

Data Index: 1107814 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1001. Min Act: -0.0003

Data Index: 36179 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0955. Min Act: -0.0003

Data Index: 1316545 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0978. Min Act: -0.0002

Data Index: 986096 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0932. Min Act: -0.0003

Data Index: 455768 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1004. Min Act: -0.0003

Data Index: 1010694 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0953. Min Act: -0.0003

Data Index: 198888 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0931. Min Act: -0.0003

Data Index: 198796 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0933. Min Act: -0.0002

Data Index: 800968 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0963. Min Act: -0.0002

Data Index: 772310 (C4 (Web Text))

Max Activating Token Index: 231