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

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

Neuron 1098 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0006

Data Index: 80138 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0749. Min Act: -0.0006

Data Index: 1198805 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0702. Min Act: -0.0006

Data Index: 428746 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0605. Min Act: -0.0006

Data Index: 461068 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0678. Min Act: -0.0006

Data Index: 492137 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0650. Min Act: -0.0006

Data Index: 637763 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0654. Min Act: -0.0006

Data Index: 410253 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0651. Min Act: -0.0006

Data Index: 144075 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0594. Min Act: -0.0006

Data Index: 753298 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0641. Min Act: -0.0005

Data Index: 677037 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0612. Min Act: -0.0006

Data Index: 1054775 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0630. Min Act: -0.0006

Data Index: 437485 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0604. Min Act: -0.0006

Data Index: 998147 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0624. Min Act: -0.0006

Data Index: 480417 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0593. Min Act: -0.0006

Data Index: 142848 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0585. Min Act: -0.0006

Data Index: 75123 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0601. Min Act: -0.0006

Data Index: 418400 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0586. Min Act: -0.0006

Data Index: 1175785 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0609. Min Act: -0.0006

Data Index: 1012608 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0603. Min Act: -0.0006

Data Index: 728129 (C4 (Web Text))

Max Activating Token Index: 473