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

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

Neuron 72 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: 0.0091. Min Range: -0.0091

Max Act: 0.0091. Min Act: -0.0006

Data Index: 233751 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1299686 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0006

Data Index: 646050 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0077. Min Act: -0.0006

Data Index: 698390 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1039640 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0075. Min Act: -0.0006

Data Index: 306396 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0074. Min Act: -0.0006

Data Index: 401409 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1328731 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0074. Min Act: -0.0006

Data Index: 801793 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0073. Min Act: -0.0006

Data Index: 377343 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0073. Min Act: -0.0006

Data Index: 126468 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0072. Min Act: -0.0006

Data Index: 851749 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0072. Min Act: -0.0006

Data Index: 627058 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0071. Min Act: -0.0006

Data Index: 589781 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0071. Min Act: -0.0006

Data Index: 6423 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1351893 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0069. Min Act: -0.0006

Data Index: 137784 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1180159 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1196777 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0068. Min Act: -0.0006

Data Index: 743551 (C4 (Web Text))

Max Activating Token Index: 569