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

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

Neuron 2610 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0051. Min Act: -0.0002

Data Index: 468139 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 389125 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1201154 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1232730 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0047. Min Act: -0.0002

Data Index: 107377 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1061478 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1050174 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0045. Min Act: -0.0002

Data Index: 71256 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0045. Min Act: -0.0002

Data Index: 416332 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1273667 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0043. Min Act: -0.0002

Data Index: 738176 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0042. Min Act: -0.0002

Data Index: 1188810 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0043. Min Act: -0.0002

Data Index: 497846 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0043. Min Act: -0.0002

Data Index: 713020 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0043. Min Act: -0.0002

Data Index: 55703 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0040. Min Act: -0.0002

Data Index: 352344 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0040. Min Act: -0.0002

Data Index: 986818 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0039. Min Act: -0.0002

Data Index: 205845 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0040. Min Act: -0.0002

Data Index: 511999 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0040. Min Act: -0.0002

Data Index: 411723 (C4 (Web Text))

Max Activating Token Index: 5