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

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

Neuron 3401 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.5726. Min Act: -0.0002

Data Index: 1232178 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.4068. Min Act: -0.0002

Data Index: 1055468 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.4115. Min Act: -0.0002

Data Index: 204673 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.1738. Min Act: -0.0002

Data Index: 1031106 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.3812. Min Act: -0.0002

Data Index: 231518 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.4046. Min Act: -0.0002

Data Index: 1064032 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.1703. Min Act: -0.0002

Data Index: 1347071 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.3282. Min Act: -0.0002

Data Index: 772207 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.2070. Min Act: -0.0002

Data Index: 1328002 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.3470. Min Act: -0.0002

Data Index: 1254486 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.3206. Min Act: -0.0002

Data Index: 1169089 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.2156. Min Act: -0.0002

Data Index: 765303 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.3082. Min Act: -0.0002

Data Index: 191590 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.1427. Min Act: -0.0002

Data Index: 525620 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.2208. Min Act: -0.0002

Data Index: 670597 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.2710. Min Act: -0.0002

Data Index: 604395 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.3074. Min Act: -0.0002

Data Index: 156490 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.4160. Min Act: -0.0002

Data Index: 781816 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.2522. Min Act: -0.0002

Data Index: 499932 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 1.5726. Min Range: -1.5726

Max Act: 1.1507. Min Act: -0.0002

Data Index: 1172729 (C4 (Web Text))

Max Activating Token Index: 61