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

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

Neuron 5324 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: 0.1089. Min Range: -0.1089

Max Act: 0.1089. Min Act: -0.0002

Data Index: 970821 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1082. Min Act: -0.0002

Data Index: 808332 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1029. Min Act: -0.0002

Data Index: 919858 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0973. Min Act: -0.0002

Data Index: 129901 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1051741 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0989. Min Act: -0.0002

Data Index: 226167 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0970. Min Act: -0.0002

Data Index: 284941 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1342994 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0912. Min Act: -0.0002

Data Index: 313655 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1352987 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0871. Min Act: -0.0002

Data Index: 97657 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0867. Min Act: -0.0002

Data Index: 828017 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0927. Min Act: -0.0002

Data Index: 457195 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1227013 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0827. Min Act: -0.0002

Data Index: 583317 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1264966 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1224535 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0813. Min Act: -0.0002

Data Index: 584988 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0830. Min Act: -0.0002

Data Index: 950676 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0833. Min Act: -0.0002

Data Index: 213245 (C4 (Web Text))

Max Activating Token Index: 706