Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1397. Min Act: -0.0003

Data Index: 1029581 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1175. Min Act: -0.0003

Data Index: 273037 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1252. Min Act: -0.0003

Data Index: 1203325 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1206. Min Act: -0.0003

Data Index: 96225 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1172. Min Act: -0.0003

Data Index: 340709 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1164. Min Act: -0.0003

Data Index: 739158 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1141. Min Act: -0.0003

Data Index: 260935 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1123. Min Act: -0.0003

Data Index: 1103949 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1011. Min Act: -0.0003

Data Index: 1053963 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1054. Min Act: -0.0003

Data Index: 878049 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1032. Min Act: -0.0003

Data Index: 528161 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1053. Min Act: -0.0003

Data Index: 322745 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1042. Min Act: -0.0003

Data Index: 711748 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1000. Min Act: -0.0003

Data Index: 430406 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0928. Min Act: -0.0003

Data Index: 84973 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0993. Min Act: -0.0003

Data Index: 1333928 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1001. Min Act: -0.0003

Data Index: 243099 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0961. Min Act: -0.0003

Data Index: 668302 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1033. Min Act: -0.0003

Data Index: 153964 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0932. Min Act: -0.0003

Data Index: 739251 (C4 (Web Text))

Max Activating Token Index: 122