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

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

Neuron 3643 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3445. Min Act: -0.0001

Data Index: 198923 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3065. Min Act: -0.0000

Data Index: 427470 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3018. Min Act: -0.0000

Data Index: 72787 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1269345 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1343775 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2718. Min Act: -0.0000

Data Index: 540454 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2706. Min Act: -0.0001

Data Index: 782650 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1314097 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2691. Min Act: -0.0000

Data Index: 24493 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2657. Min Act: -0.0001

Data Index: 32666 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2568. Min Act: -0.0000

Data Index: 144851 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1110577 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1010501 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2700. Min Act: -0.0000

Data Index: 464557 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1238962 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2529. Min Act: -0.0001

Data Index: 903023 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2702. Min Act: -0.0000

Data Index: 81068 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2594. Min Act: 0.0000

Data Index: 671624 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1133116 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1268187 (C4 (Web Text))

Max Activating Token Index: 466