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

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

Neuron 596 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: 0.1230. Min Range: -0.1230

Max Act: 0.1057. Min Act: -0.0003

Data Index: 1055833 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1230. Min Act: -0.0003

Data Index: 205296 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0981. Min Act: -0.0003

Data Index: 1090197 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1093. Min Act: -0.0002

Data Index: 241264 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1002. Min Act: -0.0003

Data Index: 9218 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1046. Min Act: -0.0003

Data Index: 166442 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0955. Min Act: -0.0002

Data Index: 690746 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0979. Min Act: -0.0002

Data Index: 253074 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1006. Min Act: -0.0003

Data Index: 344106 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0927. Min Act: -0.0003

Data Index: 983909 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.1006. Min Act: -0.0002

Data Index: 1104137 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0895. Min Act: -0.0003

Data Index: 143532 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1217818 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0785. Min Act: -0.0002

Data Index: 548072 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0931. Min Act: -0.0003

Data Index: 750299 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0846. Min Act: -0.0003

Data Index: 540369 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1352746 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1008225 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1002298 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.1230. Min Range: -0.1230

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1083071 (C4 (Web Text))

Max Activating Token Index: 778