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

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

Neuron 3582 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.8971. Min Act: -0.0001

Data Index: 1083424 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.5939. Min Act: -0.0001

Data Index: 995837 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.7039. Min Act: -0.0002

Data Index: 574369 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.5713. Min Act: -0.0001

Data Index: 293097 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.4596. Min Act: -0.0002

Data Index: 133659 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.6535. Min Act: -0.0001

Data Index: 883175 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.6040. Min Act: -0.0002

Data Index: 1209698 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.7025. Min Act: -0.0002

Data Index: 91325 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.4974. Min Act: -0.0001

Data Index: 299976 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.6892. Min Act: -0.0002

Data Index: 1353997 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.5411. Min Act: -0.0001

Data Index: 76183 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.6076. Min Act: -0.0002

Data Index: 1250723 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.5067. Min Act: -0.0002

Data Index: 458325 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.5429. Min Act: -0.0002

Data Index: 597507 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.4597. Min Act: -0.0002

Data Index: 281709 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.5591. Min Act: -0.0002

Data Index: 1143333 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.4049. Min Act: -0.0002

Data Index: 1232489 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.4709. Min Act: -0.0002

Data Index: 1145358 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.4418. Min Act: -0.0002

Data Index: 134562 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.4127. Min Act: -0.0001

Data Index: 516740 (C4 (Web Text))

Max Activating Token Index: 479