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

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

Neuron 55 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1463194 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1358268 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0095. Min Act: -0.0006

Data Index: 356445 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1056950 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0090. Min Act: -0.0006

Data Index: 696787 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1190235 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0089. Min Act: -0.0006

Data Index: 955412 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0085. Min Act: -0.0006

Data Index: 773429 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1012858 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0085. Min Act: -0.0006

Data Index: 46487 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1225693 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1178499 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1013925 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1031519 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0082. Min Act: -0.0006

Data Index: 732782 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0082. Min Act: -0.0006

Data Index: 595348 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1327417 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1163184 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0081. Min Act: -0.0006

Data Index: 201832 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0081. Min Act: -0.0006

Data Index: 272635 (C4 (Web Text))

Max Activating Token Index: 20