Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2717 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0100. Min Act: -0.0003

Data Index: 1043663 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0082. Min Act: -0.0003

Data Index: 262210 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0073. Min Act: -0.0003

Data Index: 930607 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0071. Min Act: -0.0002

Data Index: 390958 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0071. Min Act: -0.0003

Data Index: 32177 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1274069 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1141073 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1061223 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1097498 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1152765 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1259850 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0065. Min Act: -0.0003

Data Index: 407082 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0065. Min Act: -0.0003

Data Index: 791406 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0064. Min Act: -0.0002

Data Index: 843610 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0064. Min Act: -0.0003

Data Index: 80479 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1060616 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1099187 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0063. Min Act: -0.0003

Data Index: 209483 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0062. Min Act: -0.0002

Data Index: 749740 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1655450 (Python Code)

Max Activating Token Index: 1023