Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5422 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4716. Min Act: -0.0002

Data Index: 916519 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4467. Min Act: -0.0002

Data Index: 788707 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4069. Min Act: -0.0002

Data Index: 1075327 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3727. Min Act: -0.0002

Data Index: 823367 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3567. Min Act: -0.0002

Data Index: 49934 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3591. Min Act: -0.0002

Data Index: 671957 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3615. Min Act: -0.0002

Data Index: 1314260 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3328. Min Act: -0.0002

Data Index: 1171355 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3653. Min Act: -0.0002

Data Index: 1284174 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3280. Min Act: -0.0002

Data Index: 1304061 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3276. Min Act: -0.0002

Data Index: 1207456 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.2905. Min Act: -0.0002

Data Index: 135160 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3135. Min Act: -0.0002

Data Index: 1085579 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3040. Min Act: -0.0002

Data Index: 843910 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3239. Min Act: -0.0002

Data Index: 752911 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3001. Min Act: -0.0002

Data Index: 1051875 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3063. Min Act: -0.0002

Data Index: 331138 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3068. Min Act: -0.0002

Data Index: 540355 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.2952. Min Act: -0.0002

Data Index: 507284 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3111. Min Act: -0.0002

Data Index: 325344 (C4 (Web Text))

Max Activating Token Index: 670