Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 577 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0897. Min Act: -0.0001

Data Index: 663607 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0888. Min Act: -0.0001

Data Index: 905506 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0835. Min Act: -0.0001

Data Index: 650128 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1327769 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0834. Min Act: -0.0001

Data Index: 602422 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1167777 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0831. Min Act: -0.0001

Data Index: 39215 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1177896 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0815. Min Act: -0.0001

Data Index: 956378 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0786. Min Act: -0.0002

Data Index: 260863 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0778. Min Act: -0.0001

Data Index: 463068 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1108315 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0780. Min Act: -0.0001

Data Index: 622148 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0791. Min Act: -0.0001

Data Index: 556270 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0817. Min Act: -0.0001

Data Index: 485607 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0760. Min Act: -0.0001

Data Index: 888534 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0793. Min Act: -0.0001

Data Index: 405648 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0765. Min Act: -0.0001

Data Index: 70203 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0776. Min Act: -0.0002

Data Index: 735027 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1101897 (C4 (Web Text))

Max Activating Token Index: 128