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

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

Neuron 4604 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: 0.5034. Min Range: -0.5034

Max Act: 0.5034. Min Act: -0.0000

Data Index: 466952 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4717. Min Act: 0.0001

Data Index: 1300549 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4684. Min Act: -0.0000

Data Index: 962187 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4615. Min Act: -0.0000

Data Index: 821349 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4490. Min Act: -0.0000

Data Index: 942860 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4617. Min Act: -0.0000

Data Index: 526620 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4743. Min Act: -0.0000

Data Index: 597129 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4227. Min Act: -0.0000

Data Index: 36352 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4559. Min Act: -0.0000

Data Index: 457377 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4549. Min Act: -0.0000

Data Index: 467766 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4616. Min Act: 0.0000

Data Index: 1311488 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1264585 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1233884 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4412. Min Act: -0.0000

Data Index: 357393 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1080236 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1010569 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1321253 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4116. Min Act: -0.0000

Data Index: 981689 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4378. Min Act: -0.0000

Data Index: 203908 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.5034. Min Range: -0.5034

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1345129 (C4 (Web Text))

Max Activating Token Index: 288