Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 990 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.5433. Min Act: 0.0000

Data Index: 258572 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4844. Min Act: 0.0002

Data Index: 985871 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4650. Min Act: -0.0000

Data Index: 558883 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4835. Min Act: -0.0000

Data Index: 934510 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4599. Min Act: 0.0001

Data Index: 796361 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4678. Min Act: -0.0000

Data Index: 911366 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4608. Min Act: -0.0000

Data Index: 355661 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4533. Min Act: 0.0000

Data Index: 347957 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4439. Min Act: -0.0000

Data Index: 180202 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4014. Min Act: -0.0000

Data Index: 948693 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3702. Min Act: -0.0000

Data Index: 742833 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1111217 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3690. Min Act: 0.0000

Data Index: 658385 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3598. Min Act: -0.0000

Data Index: 162195 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3656. Min Act: -0.0000

Data Index: 194572 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3645. Min Act: -0.0000

Data Index: 864370 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3720. Min Act: -0.0000

Data Index: 23570 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3456. Min Act: -0.0000

Data Index: 664081 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1038360 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3523. Min Act: 0.0002

Data Index: 978890 (C4 (Web Text))

Max Activating Token Index: 38