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

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

Neuron 1893 in Layer 1

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: 254455 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1400652 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1503138 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1313874 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0046. Min Act: -0.0002

Data Index: 606088 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1203132 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1396535 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0003

Data Index: 637820 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0045. Min Act: -0.0003

Data Index: 661456 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0003

Data Index: 992231 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1298626 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0044. Min Act: -0.0003

Data Index: 554843 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0044. Min Act: -0.0002

Data Index: 645967 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1579357 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0043. Min Act: -0.0003

Data Index: 411488 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1161598 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0042. Min Act: -0.0002

Data Index: 1071695 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0043. Min Act: -0.0003

Data Index: 550403 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0042. Min Act: -0.0003

Data Index: 28888 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1405513 (Python Code)

Max Activating Token Index: 22