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

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

Neuron 4807 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: 0.0080. Min Range: -0.0080

Max Act: 0.0080. Min Act: -0.0002

Data Index: 1118099 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0079. Min Act: -0.0002

Data Index: 740502 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0074. Min Act: -0.0002

Data Index: 911322 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1298396 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0074. Min Act: -0.0002

Data Index: 520801 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0073. Min Act: -0.0002

Data Index: 311691 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0071. Min Act: -0.0002

Data Index: 229901 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1349319 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 127577 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 604193 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 374326 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 110755 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0067. Min Act: -0.0002

Data Index: 364391 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 484665 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0067. Min Act: -0.0002

Data Index: 334782 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0066. Min Act: -0.0002

Data Index: 301091 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1327509 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0067. Min Act: -0.0002

Data Index: 136276 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1199061 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0066. Min Act: -0.0002

Data Index: 215467 (C4 (Web Text))

Max Activating Token Index: 20