Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2010 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1142. Min Act: -0.0003

Data Index: 18929 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1126. Min Act: -0.0003

Data Index: 1312638 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1080. Min Act: -0.0003

Data Index: 1226719 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1051. Min Act: -0.0003

Data Index: 761747 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1020. Min Act: -0.0003

Data Index: 1129551 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1030. Min Act: -0.0003

Data Index: 944439 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0968. Min Act: -0.0003

Data Index: 903924 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0977. Min Act: -0.0004

Data Index: 146511 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1002. Min Act: -0.0004

Data Index: 869985 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0971. Min Act: -0.0003

Data Index: 623074 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0928. Min Act: -0.0003

Data Index: 1135914 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0911. Min Act: -0.0003

Data Index: 1065020 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0919. Min Act: -0.0003

Data Index: 438281 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0924. Min Act: -0.0003

Data Index: 453442 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0912. Min Act: -0.0003

Data Index: 940733 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0931. Min Act: -0.0003

Data Index: 1037941 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0881. Min Act: -0.0003

Data Index: 600412 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0907. Min Act: -0.0004

Data Index: 1265813 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0909. Min Act: -0.0004

Data Index: 1328673 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0906. Min Act: -0.0003

Data Index: 164792 (C4 (Web Text))

Max Activating Token Index: 204