Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4490 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0804. Min Act: -0.0001

Data Index: 191487 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0001

Data Index: 458001 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0692. Min Act: -0.0001

Data Index: 31533 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0752. Min Act: -0.0001

Data Index: 945114 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0773. Min Act: -0.0001

Data Index: 213215 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0762. Min Act: -0.0001

Data Index: 170563 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0737. Min Act: -0.0001

Data Index: 990089 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0755. Min Act: -0.0001

Data Index: 841120 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1216323 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0719. Min Act: -0.0001

Data Index: 697111 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1350744 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0699. Min Act: -0.0001

Data Index: 770426 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0725. Min Act: -0.0001

Data Index: 797541 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1113286 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1097660 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1082849 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0686. Min Act: -0.0001

Data Index: 165453 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0624. Min Act: -0.0001

Data Index: 724645 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0564. Min Act: -0.0001

Data Index: 112438 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0700. Min Act: -0.0001

Data Index: 463256 (C4 (Web Text))

Max Activating Token Index: 125