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

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

Neuron 3622 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: 0.1312. Min Range: -0.1312

Max Act: 0.1312. Min Act: -0.0001

Data Index: 603103 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1187. Min Act: -0.0002

Data Index: 315080 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1105. Min Act: -0.0001

Data Index: 820615 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1142. Min Act: -0.0001

Data Index: 316458 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1059. Min Act: -0.0002

Data Index: 638466 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1023. Min Act: -0.0002

Data Index: 454862 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1012. Min Act: -0.0002

Data Index: 1026063 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1042. Min Act: -0.0002

Data Index: 983895 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0961. Min Act: -0.0002

Data Index: 813466 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1008. Min Act: -0.0002

Data Index: 698297 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0962. Min Act: -0.0002

Data Index: 656480 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1123541 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0981. Min Act: -0.0001

Data Index: 678098 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1028041 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0869. Min Act: -0.0001

Data Index: 84420 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1126427 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0854. Min Act: -0.0002

Data Index: 905196 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0892. Min Act: -0.0001

Data Index: 45649 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0912. Min Act: -0.0002

Data Index: 678868 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0846. Min Act: -0.0002

Data Index: 706484 (C4 (Web Text))

Max Activating Token Index: 187