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

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

Neuron 20 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1176. Min Act: -0.0003

Data Index: 834729 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1138. Min Act: -0.0003

Data Index: 858975 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1053. Min Act: -0.0003

Data Index: 233754 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1081. Min Act: -0.0003

Data Index: 971951 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1055. Min Act: -0.0003

Data Index: 892166 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0984. Min Act: -0.0003

Data Index: 616839 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0997. Min Act: -0.0003

Data Index: 348734 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0999. Min Act: -0.0003

Data Index: 997119 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0984. Min Act: -0.0003

Data Index: 147239 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0950. Min Act: -0.0002

Data Index: 97031 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0970. Min Act: -0.0003

Data Index: 534290 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0967. Min Act: -0.0003

Data Index: 520502 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0973. Min Act: -0.0003

Data Index: 1016926 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0950. Min Act: -0.0003

Data Index: 101377 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0946. Min Act: -0.0003

Data Index: 915920 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0944. Min Act: -0.0003

Data Index: 1158174 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0941. Min Act: -0.0003

Data Index: 888195 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0950. Min Act: -0.0003

Data Index: 852637 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0940. Min Act: -0.0003

Data Index: 1217227 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0907. Min Act: -0.0003

Data Index: 692856 (C4 (Web Text))

Max Activating Token Index: 542