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

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

Neuron 3564 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: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1442534 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1550949 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1503457 (Python Code)

Max Activating Token Index: 1022

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0042. Min Act: -0.0002

Data Index: 1559442 (Python Code)

Max Activating Token Index: 975

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0002

Data Index: 1597950 (Python Code)

Max Activating Token Index: 577

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0002

Data Index: 1454253 (Python Code)

Max Activating Token Index: 1005

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0002

Data Index: 1574723 (Python Code)

Max Activating Token Index: 1003

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0040. Min Act: -0.0002

Data Index: 1603808 (Python Code)

Max Activating Token Index: 691

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0040. Min Act: -0.0003

Data Index: 1211062 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0040. Min Act: -0.0002

Data Index: 1528359 (Python Code)

Max Activating Token Index: 999

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0040. Min Act: -0.0002

Data Index: 1613426 (Python Code)

Max Activating Token Index: 1004

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1635116 (Python Code)

Max Activating Token Index: 869

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1637916 (Python Code)

Max Activating Token Index: 983

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1430320 (Python Code)

Max Activating Token Index: 857

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1508886 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1561940 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1518228 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1638952 (Python Code)

Max Activating Token Index: 464

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1618903 (Python Code)

Max Activating Token Index: 968

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1598247 (Python Code)

Max Activating Token Index: 997