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

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

Neuron 1239 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: 0.0033. Min Range: -0.0033

Max Act: 0.0033. Min Act: -0.0002

Data Index: 1542399 (Python Code)

Max Activating Token Index: 93

Text #1

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0028. Min Act: -0.0002

Data Index: 1652747 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0027. Min Act: -0.0002

Data Index: 368603 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1593635 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1446067 (Python Code)

Max Activating Token Index: 58

Text #5

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0002

Data Index: 730127 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1423430 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0002

Data Index: 388228 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1598625 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1617962 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1558818 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1490690 (Python Code)

Max Activating Token Index: 144

Text #12

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1299399 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1407488 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0002

Data Index: 155439 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1557090 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0002

Data Index: 539078 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1424296 (Python Code)

Max Activating Token Index: 195

Text #18

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1397735 (Python Code)

Max Activating Token Index: 49

Text #19

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1374291 (Python Code)

Max Activating Token Index: 67