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

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

Neuron 3425 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2570. Min Act: -0.0000

Data Index: 958884 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.3506. Min Act: -0.0000

Data Index: 919685 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.2928. Min Act: -0.0000

Data Index: 43006 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.1327. Min Act: -0.0000

Data Index: 376571 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.0511. Min Act: -0.0000

Data Index: 616639 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.1031. Min Act: -0.0000

Data Index: 567274 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.1150. Min Act: 0.0001

Data Index: 1109919 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.1076. Min Act: -0.0000

Data Index: 250423 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.0640. Min Act: -0.0000

Data Index: 31336 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.0312. Min Act: -0.0000

Data Index: 991787 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.0314. Min Act: 0.0001

Data Index: 862995 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 1.3506. Min Range: -1.3506

Max Act: 0.9597. Min Act: -0.0000

Data Index: 501030 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.0103. Min Act: -0.0000

Data Index: 942903 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 1.3506. Min Range: -1.3506

Max Act: 0.9434. Min Act: -0.0000

Data Index: 641094 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.0432. Min Act: 0.0001

Data Index: 298523 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 1.3506. Min Range: -1.3506

Max Act: 0.9694. Min Act: -0.0000

Data Index: 101936 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 1.3506. Min Range: -1.3506

Max Act: 0.9648. Min Act: -0.0000

Data Index: 441422 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.3506. Min Range: -1.3506

Max Act: 1.0314. Min Act: -0.0000

Data Index: 820022 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 1.3506. Min Range: -1.3506

Max Act: 0.9661. Min Act: -0.0000

Data Index: 193881 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 1.3506. Min Range: -1.3506

Max Act: 0.9549. Min Act: -0.0000

Data Index: 76634 (C4 (Web Text))

Max Activating Token Index: 512