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

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

Neuron 4152 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: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1546135 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1625007 (Python Code)

Max Activating Token Index: 809

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1495580 (Python Code)

Max Activating Token Index: 704

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1548736 (Python Code)

Max Activating Token Index: 870

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1585944 (Python Code)

Max Activating Token Index: 769

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1496767 (Python Code)

Max Activating Token Index: 842

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1511544 (Python Code)

Max Activating Token Index: 782

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1644461 (Python Code)

Max Activating Token Index: 738

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1629086 (Python Code)

Max Activating Token Index: 711

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1494197 (Python Code)

Max Activating Token Index: 746

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1491542 (Python Code)

Max Activating Token Index: 816

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1378048 (Python Code)

Max Activating Token Index: 812

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1520412 (Python Code)

Max Activating Token Index: 714

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0002

Data Index: 343476 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1543974 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1644154 (Python Code)

Max Activating Token Index: 656

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1530512 (Python Code)

Max Activating Token Index: 674

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1414534 (Python Code)

Max Activating Token Index: 807

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1573190 (Python Code)

Max Activating Token Index: 900

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1583233 (Python Code)

Max Activating Token Index: 572