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

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

Neuron 3437 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.0224. Min Act: -0.0002

Data Index: 945927 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9298. Min Act: -0.0002

Data Index: 454706 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9821. Min Act: -0.0002

Data Index: 435367 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9116. Min Act: -0.0002

Data Index: 12555 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.1187. Min Act: -0.0002

Data Index: 539086 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9139. Min Act: -0.0002

Data Index: 37200 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.1128. Min Act: -0.0002

Data Index: 129991 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.0660. Min Act: -0.0002

Data Index: 995991 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.0792. Min Act: -0.0002

Data Index: 943532 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8877. Min Act: -0.0002

Data Index: 1229775 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9633. Min Act: -0.0002

Data Index: 1336917 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8893. Min Act: -0.0002

Data Index: 522904 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9741. Min Act: -0.0002

Data Index: 253755 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8040. Min Act: -0.0002

Data Index: 1228648 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.0381. Min Act: -0.0002

Data Index: 58941 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9175. Min Act: -0.0002

Data Index: 917666 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9649. Min Act: -0.0002

Data Index: 525044 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9981. Min Act: -0.0002

Data Index: 356699 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9617. Min Act: -0.0002

Data Index: 716228 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8013. Min Act: -0.0002

Data Index: 1228040 (C4 (Web Text))

Max Activating Token Index: 198