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

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

Neuron 5030 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.9642. Min Act: -0.0000

Data Index: 668432 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.9442. Min Act: -0.0000

Data Index: 709496 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1331221 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.9194. Min Act: -0.0000

Data Index: 439344 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8631. Min Act: -0.0000

Data Index: 753597 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8655. Min Act: -0.0000

Data Index: 932400 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8360. Min Act: -0.0000

Data Index: 715175 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8823. Min Act: -0.0000

Data Index: 372563 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8728. Min Act: -0.0000

Data Index: 511490 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8979. Min Act: -0.0000

Data Index: 336201 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1288414 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8592. Min Act: -0.0000

Data Index: 140462 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8849. Min Act: -0.0000

Data Index: 290300 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1275588 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8039. Min Act: -0.0000

Data Index: 305214 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7872. Min Act: -0.0000

Data Index: 289028 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7998. Min Act: -0.0000

Data Index: 786059 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7962. Min Act: -0.0000

Data Index: 608636 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7638. Min Act: -0.0000

Data Index: 438933 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7626. Min Act: -0.0000

Data Index: 815264 (C4 (Web Text))

Max Activating Token Index: 26