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

Dataset: The Pile

Neuron 2511 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0077. Min Act: -0.0000

Data Index: 1705540 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0071. Min Act: -0.0000

Data Index: 237594 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0070. Min Act: -0.0000

Data Index: 227595 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0000

Data Index: 409035 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0000

Data Index: 993893 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0000

Data Index: 292074 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0000

Data Index: 1832259 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0000

Data Index: 992364 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0000

Data Index: 1908109 (The Pile)

Max Activating Token Index: 20

Text #9

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0000

Data Index: 1087541 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0000

Data Index: 1288131 (The Pile)

Max Activating Token Index: 15

Text #11

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0000

Data Index: 129185 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0000

Data Index: 1581800 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0000

Data Index: 41485 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0000

Data Index: 599735 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0000

Data Index: 1195765 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0000

Data Index: 1530032 (The Pile)

Max Activating Token Index: 21

Text #17

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0000

Data Index: 950901 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0000

Data Index: 1862980 (The Pile)

Max Activating Token Index: 15

Text #19

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0000

Data Index: 1356925 (The Pile)

Max Activating Token Index: 21