Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 249 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0110. Min Act: -0.0002

Data Index: 122529 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0106. Min Act: -0.0002

Data Index: 757183 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0002

Data Index: 612950 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0002

Data Index: 8040 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0092. Min Act: -0.0002

Data Index: 134962 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1018950 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0093. Min Act: -0.0002

Data Index: 945435 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0092. Min Act: -0.0002

Data Index: 925019 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1033710 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0094. Min Act: -0.0002

Data Index: 148330 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0087. Min Act: -0.0002

Data Index: 578761 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0096. Min Act: -0.0002

Data Index: 945870 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0093. Min Act: -0.0002

Data Index: 699308 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0083. Min Act: -0.0002

Data Index: 749629 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1455908 (Python Code)

Max Activating Token Index: 969

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1389068 (Python Code)

Max Activating Token Index: 944

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1462972 (Python Code)

Max Activating Token Index: 983

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0087. Min Act: -0.0002

Data Index: 487842 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0075. Min Act: -0.0002

Data Index: 44 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0078. Min Act: -0.0002

Data Index: 843407 (C4 (Web Text))

Max Activating Token Index: 971