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

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

Neuron 2125 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: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 529943 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 415701 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 69889 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 480905 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1233385 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 200498 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 208261 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 691752 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1146552 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 545242 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1209135 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1337973 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1045904 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0049. Min Act: -0.0002

Data Index: 959917 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1308567 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0048. Min Act: -0.0002

Data Index: 840265 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0049. Min Act: -0.0002

Data Index: 857803 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0048. Min Act: -0.0002

Data Index: 15021 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0048. Min Act: -0.0002

Data Index: 508596 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1200627 (C4 (Web Text))

Max Activating Token Index: 992