Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1749 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.6842. Min Act: -0.0000

Data Index: 434202 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1079821 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.5516. Min Act: -0.0000

Data Index: 608657 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1103121 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.5289. Min Act: -0.0000

Data Index: 299404 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.5361. Min Act: -0.0000

Data Index: 692862 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.5317. Min Act: -0.0000

Data Index: 826759 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1038994 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4943. Min Act: -0.0000

Data Index: 636950 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.5070. Min Act: -0.0000

Data Index: 943770 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.5040. Min Act: -0.0000

Data Index: 630712 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1203211 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4910. Min Act: -0.0000

Data Index: 234040 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1089486 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1310606 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4963. Min Act: -0.0000

Data Index: 991035 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1118726 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4783. Min Act: -0.0000

Data Index: 309170 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1166974 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4655. Min Act: -0.0000

Data Index: 158571 (C4 (Web Text))

Max Activating Token Index: 809