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

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

Neuron 782 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3130. Min Range: -2.3130

Max Act: 2.3130. Min Act: -0.0000

Data Index: 414081 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.8558. Min Act: -0.0000

Data Index: 109033 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.7281. Min Act: -0.0000

Data Index: 273145 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 2.3130. Min Range: -2.3130

Max Act: 2.0057. Min Act: -0.0000

Data Index: 343538 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.7786. Min Act: -0.0001

Data Index: 929801 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.6882. Min Act: -0.0000

Data Index: 1183224 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.6106. Min Act: -0.0000

Data Index: 417880 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.7369. Min Act: -0.0000

Data Index: 69691 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.7144. Min Act: -0.0000

Data Index: 1215143 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.6354. Min Act: -0.0000

Data Index: 1188575 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.7123. Min Act: -0.0000

Data Index: 551164 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.7562. Min Act: -0.0000

Data Index: 476323 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.6047. Min Act: -0.0000

Data Index: 647265 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.6999. Min Act: -0.0000

Data Index: 1313161 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.5137. Min Act: -0.0000

Data Index: 499756 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.6825. Min Act: -0.0000

Data Index: 872931 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.6511. Min Act: -0.0000

Data Index: 730513 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.6311. Min Act: -0.0000

Data Index: 139105 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1237312 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 2.3130. Min Range: -2.3130

Max Act: 1.5806. Min Act: -0.0000

Data Index: 790392 (C4 (Web Text))

Max Activating Token Index: 174