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

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

Neuron 1022 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1039583 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0002

Data Index: 116407 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1078846 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0002

Data Index: 250391 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0002

Data Index: 145700 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0002

Data Index: 876979 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0002

Data Index: 42758 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0094. Min Act: -0.0002

Data Index: 450895 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1276806 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0094. Min Act: -0.0002

Data Index: 605046 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0094. Min Act: -0.0002

Data Index: 28702 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1347122 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0002

Data Index: 387041 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1357232 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1264764 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0002

Data Index: 746390 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0002

Data Index: 640494 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0002

Data Index: 707512 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1039438 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0092. Min Act: -0.0002

Data Index: 142150 (C4 (Web Text))

Max Activating Token Index: 4