Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3430 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0012. Min Act: -0.0002

Data Index: 39878 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0013. Min Act: -0.0003

Data Index: 120711 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0003

Data Index: 610245 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1002156 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0003

Data Index: 719176 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1647089 (Python Code)

Max Activating Token Index: 690

Text #6

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0002

Data Index: 614204 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0002

Data Index: 501997 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1503684 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0002

Data Index: 63606 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0003

Data Index: 1272693 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1464537 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1548778 (Python Code)

Max Activating Token Index: 241

Text #13

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0003

Data Index: 1039412 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1650203 (Python Code)

Max Activating Token Index: 202

Text #15

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1124775 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0002

Data Index: 823156 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0003

Data Index: 959928 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0003

Data Index: 680584 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1458720 (Python Code)

Max Activating Token Index: 235