Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 633 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0085. Min Act: -0.0005

Data Index: 1581386 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0080. Min Act: -0.0005

Data Index: 1430352 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0077. Min Act: -0.0006

Data Index: 745089 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0077. Min Act: -0.0005

Data Index: 1563202 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1455406 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1625526 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0072. Min Act: -0.0005

Data Index: 809214 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1421537 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1588216 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1144093 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0070. Min Act: -0.0005

Data Index: 137173 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1515182 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0070. Min Act: -0.0005

Data Index: 369629 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1505498 (Python Code)

Max Activating Token Index: 249

Text #14

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1481124 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1119627 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1303153 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0069. Min Act: -0.0005

Data Index: 505157 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1497889 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0068. Min Act: -0.0006

Data Index: 682339 (C4 (Web Text))

Max Activating Token Index: 1023