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

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

Neuron 301 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1192. Min Act: -0.0003

Data Index: 597601 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1160. Min Act: -0.0003

Data Index: 707179 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1160. Min Act: -0.0002

Data Index: 392145 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1136. Min Act: -0.0002

Data Index: 275827 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1122. Min Act: -0.0002

Data Index: 115587 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1095. Min Act: -0.0002

Data Index: 568962 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1081. Min Act: -0.0003

Data Index: 996627 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1082. Min Act: -0.0002

Data Index: 171642 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1038. Min Act: -0.0001

Data Index: 960014 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1036. Min Act: -0.0003

Data Index: 1007671 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1033. Min Act: -0.0002

Data Index: 898576 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1030. Min Act: -0.0002

Data Index: 568969 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1019. Min Act: -0.0003

Data Index: 760481 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1018. Min Act: -0.0003

Data Index: 380254 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1012. Min Act: -0.0002

Data Index: 497343 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1011. Min Act: -0.0002

Data Index: 431910 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1011. Min Act: -0.0002

Data Index: 372734 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.1008. Min Act: -0.0002

Data Index: 48559 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0960. Min Act: -0.0003

Data Index: 1131323 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.1192. Min Range: -0.1192

Max Act: 0.0992. Min Act: -0.0003

Data Index: 1061761 (C4 (Web Text))

Max Activating Token Index: 572