Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1332 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0002

Data Index: 563689 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1262. Min Act: -0.0002

Data Index: 379745 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1113. Min Act: -0.0002

Data Index: 515149 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1108. Min Act: -0.0002

Data Index: 651826 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1093. Min Act: -0.0002

Data Index: 544748 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1034. Min Act: -0.0002

Data Index: 266847 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1111418 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1040. Min Act: -0.0002

Data Index: 836780 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1244942 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1020. Min Act: -0.0002

Data Index: 780576 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0925. Min Act: -0.0002

Data Index: 901674 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1015. Min Act: -0.0002

Data Index: 839149 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1018. Min Act: -0.0001

Data Index: 893705 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0977. Min Act: -0.0002

Data Index: 735641 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0973. Min Act: -0.0002

Data Index: 270210 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0960. Min Act: -0.0002

Data Index: 622444 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0964. Min Act: -0.0002

Data Index: 10779 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0968. Min Act: -0.0002

Data Index: 559599 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0951. Min Act: -0.0002

Data Index: 697717 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0947. Min Act: -0.0001

Data Index: 748233 (C4 (Web Text))

Max Activating Token Index: 534