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

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

Neuron 1105 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1226. Min Act: -0.0002

Data Index: 1086238 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1063. Min Act: -0.0002

Data Index: 22359 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0969. Min Act: -0.0003

Data Index: 826464 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0952. Min Act: -0.0003

Data Index: 696904 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0921. Min Act: -0.0003

Data Index: 427269 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0862. Min Act: -0.0003

Data Index: 1059501 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0868. Min Act: -0.0003

Data Index: 989988 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0830. Min Act: -0.0003

Data Index: 634939 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0888. Min Act: -0.0003

Data Index: 270041 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1022373 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0841. Min Act: -0.0003

Data Index: 517028 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0809. Min Act: -0.0003

Data Index: 741939 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1006914 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0860. Min Act: -0.0003

Data Index: 209470 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0871. Min Act: -0.0003

Data Index: 1079195 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0798. Min Act: -0.0003

Data Index: 30129 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0826. Min Act: -0.0002

Data Index: 791656 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0822. Min Act: -0.0003

Data Index: 408960 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0813. Min Act: -0.0003

Data Index: 497186 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0815. Min Act: -0.0003

Data Index: 1313372 (C4 (Web Text))

Max Activating Token Index: 599