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

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

Neuron 3564 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.5300. Min Act: -0.0000

Data Index: 411492 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.3001. Min Act: -0.0001

Data Index: 1319997 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.9771. Min Act: -0.0001

Data Index: 1289019 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.4218. Min Act: -0.0001

Data Index: 1200139 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.6301. Min Act: -0.0000

Data Index: 1151677 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.7863. Min Act: -0.0000

Data Index: 20561 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.2052. Min Act: -0.0001

Data Index: 647687 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.1242. Min Act: -0.0000

Data Index: 279580 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 5.9771. Min Range: -5.9771

Max Act: 4.9380. Min Act: -0.0001

Data Index: 677202 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.0580. Min Act: -0.0001

Data Index: 9534 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.0359. Min Act: -0.0001

Data Index: 1034455 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.3618. Min Act: -0.0001

Data Index: 807443 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 5.9771. Min Range: -5.9771

Max Act: 4.7776. Min Act: -0.0000

Data Index: 1051622 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 5.9771. Min Range: -5.9771

Max Act: 4.9903. Min Act: -0.0001

Data Index: 418588 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 5.9771. Min Range: -5.9771

Max Act: 4.7726. Min Act: -0.0001

Data Index: 355992 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 5.9771. Min Range: -5.9771

Max Act: 4.7805. Min Act: -0.0000

Data Index: 947049 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 5.9771. Min Range: -5.9771

Max Act: 5.2934. Min Act: -0.0000

Data Index: 580958 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 5.9771. Min Range: -5.9771

Max Act: 4.9441. Min Act: -0.0000

Data Index: 444277 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 5.9771. Min Range: -5.9771

Max Act: 4.7360. Min Act: -0.0001

Data Index: 465872 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 5.9771. Min Range: -5.9771

Max Act: 4.9102. Min Act: -0.0001

Data Index: 54618 (C4 (Web Text))

Max Activating Token Index: 272