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

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

Neuron 3499 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: 0.0108. Min Range: -0.0108

Max Act: 0.0108. Min Act: -0.0002

Data Index: 87012 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0102. Min Act: -0.0002

Data Index: 989046 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0101. Min Act: -0.0002

Data Index: 970475 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0101. Min Act: -0.0002

Data Index: 1417373 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0099. Min Act: -0.0002

Data Index: 400060 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0097. Min Act: -0.0002

Data Index: 80265 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0096. Min Act: -0.0002

Data Index: 362506 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1115128 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0095. Min Act: -0.0002

Data Index: 110773 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0095. Min Act: -0.0002

Data Index: 885250 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0096. Min Act: -0.0002

Data Index: 50168 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0094. Min Act: -0.0002

Data Index: 729249 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0094. Min Act: -0.0002

Data Index: 956422 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0093. Min Act: -0.0002

Data Index: 635276 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1200103 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0092. Min Act: -0.0002

Data Index: 544569 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1528345 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0091. Min Act: -0.0002

Data Index: 342304 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0091. Min Act: -0.0002

Data Index: 405185 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0091. Min Act: -0.0002

Data Index: 759536 (C4 (Web Text))

Max Activating Token Index: 497