Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4818 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.5033. Min Act: -0.0001

Data Index: 121769 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.5033. Min Act: -0.0001

Data Index: 1406273 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1655668 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4586. Min Act: -0.0001

Data Index: 163137 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4586. Min Act: -0.0000

Data Index: 1438145 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4586. Min Act: -0.0001

Data Index: 1615168 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4586. Min Act: -0.0001

Data Index: 1581742 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4586. Min Act: -0.0001

Data Index: 1634142 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4586. Min Act: -0.0001

Data Index: 1603084 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1377570 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1407131 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1598166 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4683. Min Act: -0.0001

Data Index: 590930 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1449058 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1492832 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1502296 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1603786 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1605958 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1624217 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1411417 (Python Code)

Max Activating Token Index: 1