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

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

Neuron 2108 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: 0.0073. Min Range: -0.0073

Max Act: 0.0073. Min Act: -0.0002

Data Index: 771613 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1043995 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0002

Data Index: 459863 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0002

Data Index: 398559 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1330074 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0064. Min Act: -0.0002

Data Index: 468357 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0064. Min Act: -0.0002

Data Index: 380500 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0002

Data Index: 194563 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0002

Data Index: 438437 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0002

Data Index: 666846 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0062. Min Act: -0.0002

Data Index: 186139 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1133467 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0060. Min Act: -0.0002

Data Index: 836363 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0060. Min Act: -0.0002

Data Index: 651240 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0060. Min Act: -0.0002

Data Index: 350789 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0060. Min Act: -0.0002

Data Index: 688298 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0060. Min Act: -0.0002

Data Index: 476980 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0061. Min Act: -0.0002

Data Index: 463578 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1104542 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0059. Min Act: -0.0002

Data Index: 670945 (C4 (Web Text))

Max Activating Token Index: 28