Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1863 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1104278 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0703. Min Act: -0.0002

Data Index: 259111 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0696. Min Act: -0.0002

Data Index: 837034 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1090124 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0637. Min Act: -0.0002

Data Index: 862364 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1276786 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1132343 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0628. Min Act: -0.0002

Data Index: 940830 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0617. Min Act: -0.0002

Data Index: 796389 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0630. Min Act: -0.0002

Data Index: 585062 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0604. Min Act: -0.0001

Data Index: 198300 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1333382 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1224084 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1218327 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1304342 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0571. Min Act: -0.0002

Data Index: 675302 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0561. Min Act: -0.0002

Data Index: 304269 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0567. Min Act: -0.0002

Data Index: 941274 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0573. Min Act: -0.0002

Data Index: 572281 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1265595 (C4 (Web Text))

Max Activating Token Index: 342