Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2535 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0047. Min Act: -0.0003

Data Index: 174572 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0039. Min Act: -0.0003

Data Index: 997866 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0004

Data Index: 40255 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0004

Data Index: 1025682 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1070687 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0034. Min Act: -0.0004

Data Index: 681869 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0033. Min Act: -0.0003

Data Index: 983 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0032. Min Act: -0.0003

Data Index: 106821 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0031. Min Act: -0.0003

Data Index: 208794 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0031. Min Act: -0.0003

Data Index: 341456 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0031. Min Act: -0.0003

Data Index: 435025 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0030. Min Act: -0.0003

Data Index: 156367 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0030. Min Act: -0.0003

Data Index: 1038055 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0030. Min Act: -0.0004

Data Index: 7790 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0030. Min Act: -0.0004

Data Index: 1113871 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0030. Min Act: -0.0003

Data Index: 1272750 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0030. Min Act: -0.0003

Data Index: 32999 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0029. Min Act: -0.0003

Data Index: 5873 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0029. Min Act: -0.0004

Data Index: 364213 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0029. Min Act: -0.0003

Data Index: 507615 (C4 (Web Text))

Max Activating Token Index: 385