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

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

Neuron 1063 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: 0.0065. Min Range: -0.0065

Max Act: 0.0065. Min Act: -0.0006

Data Index: 286679 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0065. Min Act: -0.0007

Data Index: 171229 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1270111 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0059. Min Act: -0.0006

Data Index: 954000 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1049937 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0060. Min Act: -0.0006

Data Index: 282773 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0058. Min Act: -0.0006

Data Index: 686683 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0058. Min Act: -0.0006

Data Index: 125985 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1406904 (Python Code)

Max Activating Token Index: 508

Text #9

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0058. Min Act: -0.0006

Data Index: 229694 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0057. Min Act: -0.0006

Data Index: 980043 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0058. Min Act: -0.0007

Data Index: 561112 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0055. Min Act: -0.0006

Data Index: 913855 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1437540 (Python Code)

Max Activating Token Index: 154

Text #14

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0057. Min Act: -0.0006

Data Index: 239673 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0057. Min Act: -0.0006

Data Index: 651491 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0056. Min Act: -0.0006

Data Index: 73330 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0057. Min Act: -0.0006

Data Index: 991564 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0056. Min Act: -0.0006

Data Index: 565600 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0056. Min Act: -0.0006

Data Index: 655117 (C4 (Web Text))

Max Activating Token Index: 929