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

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

Neuron 1512 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: 0.0051. Min Range: -0.0051

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1500763 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1485175 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1216970 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1383964 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1365783 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1574893 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1410053 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1642225 (Python Code)

Max Activating Token Index: 380

Text #8

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1635171 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1365012 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1479125 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1434364 (Python Code)

Max Activating Token Index: 314

Text #12

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1392330 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1402080 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1655774 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1571859 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1490374 (Python Code)

Max Activating Token Index: 113

Text #17

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1383596 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1520565 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1537025 (Python Code)

Max Activating Token Index: 240