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

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

Neuron 4910 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: 0.1082. Min Range: -0.1082

Max Act: 0.1082. Min Act: -0.0002

Data Index: 998520 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0923. Min Act: -0.0002

Data Index: 191144 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1146064 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0982. Min Act: -0.0002

Data Index: 185042 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0940. Min Act: -0.0002

Data Index: 865747 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0872. Min Act: -0.0002

Data Index: 595837 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1141472 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0809. Min Act: -0.0002

Data Index: 327303 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1141662 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0784. Min Act: -0.0002

Data Index: 511175 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0768. Min Act: -0.0002

Data Index: 961557 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0768. Min Act: -0.0002

Data Index: 944515 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0818. Min Act: -0.0002

Data Index: 422364 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0872. Min Act: -0.0002

Data Index: 562315 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1320707 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1349824 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0743. Min Act: -0.0002

Data Index: 674033 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0769. Min Act: -0.0002

Data Index: 909748 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0842. Min Act: -0.0002

Data Index: 866282 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0765. Min Act: -0.0002

Data Index: 632625 (C4 (Web Text))

Max Activating Token Index: 146