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

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

Neuron 4012 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: 1.0546. Min Range: -1.0546

Max Act: 1.0546. Min Act: -0.0000

Data Index: 132786 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1254852 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.6229. Min Act: -0.0000

Data Index: 157560 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.6333. Min Act: -0.0000

Data Index: 809761 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.6354. Min Act: -0.0000

Data Index: 722292 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1633939 (Python Code)

Max Activating Token Index: 517

Text #6

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1114318 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1041759 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5584. Min Act: -0.0000

Data Index: 697165 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5935. Min Act: -0.0000

Data Index: 192639 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5909. Min Act: -0.0000

Data Index: 707713 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1432973 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5520. Min Act: -0.0000

Data Index: 303870 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1637979 (Python Code)

Max Activating Token Index: 745

Text #14

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5005. Min Act: -0.0000

Data Index: 316742 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5069. Min Act: -0.0000

Data Index: 36049 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5058. Min Act: -0.0000

Data Index: 680611 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1058526 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5039. Min Act: -0.0000

Data Index: 352069 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.5022. Min Act: -0.0000

Data Index: 462017 (C4 (Web Text))

Max Activating Token Index: 26