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

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

Neuron 1982 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: 0.0089. Min Range: -0.0089

Max Act: 0.0089. Min Act: -0.0002

Data Index: 741175 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1057958 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1204603 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1132349 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0060. Min Act: -0.0002

Data Index: 502278 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0061. Min Act: -0.0002

Data Index: 4166 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0060. Min Act: -0.0002

Data Index: 766846 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1200081 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1185264 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0059. Min Act: -0.0002

Data Index: 782935 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0059. Min Act: -0.0002

Data Index: 55491 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1316776 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0057. Min Act: -0.0002

Data Index: 852820 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0054. Min Act: -0.0002

Data Index: 532088 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0056. Min Act: -0.0002

Data Index: 252524 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0054. Min Act: -0.0002

Data Index: 911061 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0054. Min Act: -0.0002

Data Index: 271115 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0054. Min Act: -0.0002

Data Index: 121212 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0053. Min Act: -0.0002

Data Index: 708842 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0053. Min Act: -0.0002

Data Index: 146192 (C4 (Web Text))

Max Activating Token Index: 46