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

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

Neuron 3608 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: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0002

Data Index: 532873 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1299270 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0002

Data Index: 126883 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 702585 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1101216 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0053. Min Act: -0.0002

Data Index: 26512 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0053. Min Act: -0.0002

Data Index: 484157 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0002

Data Index: 407154 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0002

Data Index: 782133 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0002

Data Index: 630464 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1334598 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1148805 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1431310 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0002

Data Index: 367032 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0002

Data Index: 253188 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1158903 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0002

Data Index: 353804 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0048. Min Act: -0.0002

Data Index: 217288 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0002

Data Index: 19064 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0002

Data Index: 254592 (C4 (Web Text))

Max Activating Token Index: 86