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

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

Neuron 3980 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: 0.1255. Min Range: -0.1255

Max Act: 0.1255. Min Act: -0.0002

Data Index: 943835 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1191. Min Act: -0.0002

Data Index: 14157 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1207. Min Act: -0.0002

Data Index: 937045 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1195. Min Act: -0.0002

Data Index: 390954 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1028102 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1017. Min Act: -0.0002

Data Index: 966681 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1033. Min Act: -0.0002

Data Index: 146864 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1312161 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0929. Min Act: -0.0002

Data Index: 118698 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1019. Min Act: -0.0002

Data Index: 254067 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0949. Min Act: -0.0002

Data Index: 471498 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1037. Min Act: -0.0002

Data Index: 408427 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1096324 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0969. Min Act: -0.0002

Data Index: 494323 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0962. Min Act: -0.0002

Data Index: 702593 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1270770 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1281638 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0946. Min Act: -0.0002

Data Index: 813239 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1042. Min Act: -0.0002

Data Index: 529649 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0931. Min Act: -0.0002

Data Index: 537365 (C4 (Web Text))

Max Activating Token Index: 806