Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1590 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0089. Min Act: -0.0002

Data Index: 117873 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0085. Min Act: -0.0003

Data Index: 593783 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0085. Min Act: -0.0003

Data Index: 766504 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1357720 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0083. Min Act: -0.0003

Data Index: 567103 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0081. Min Act: -0.0003

Data Index: 91836 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0081. Min Act: -0.0003

Data Index: 654390 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0081. Min Act: -0.0003

Data Index: 333539 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0080. Min Act: -0.0003

Data Index: 887729 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1267845 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1579731 (Python Code)

Max Activating Token Index: 261

Text #11

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0078. Min Act: -0.0003

Data Index: 275105 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0077. Min Act: -0.0003

Data Index: 51464 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0077. Min Act: -0.0003

Data Index: 152525 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0076. Min Act: -0.0003

Data Index: 319152 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0075. Min Act: -0.0003

Data Index: 758099 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0076. Min Act: -0.0003

Data Index: 340956 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0075. Min Act: -0.0003

Data Index: 36585 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0075. Min Act: -0.0003

Data Index: 553608 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0075. Min Act: -0.0003

Data Index: 549380 (C4 (Web Text))

Max Activating Token Index: 409