Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 923 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0908. Min Act: -0.0000

Data Index: 807353 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0845. Min Act: -0.0000

Data Index: 536084 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1094114 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0792. Min Act: -0.0000

Data Index: 490134 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0800. Min Act: -0.0001

Data Index: 844585 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0704. Min Act: -0.0000

Data Index: 26035 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0717. Min Act: -0.0001

Data Index: 662672 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0672. Min Act: -0.0000

Data Index: 303625 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0653. Min Act: -0.0001

Data Index: 46618 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0588. Min Act: -0.0001

Data Index: 551972 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1228040 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0473. Min Act: -0.0000

Data Index: 278617 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0463. Min Act: -0.0000

Data Index: 228797 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0461. Min Act: -0.0001

Data Index: 391624 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1598145 (Python Code)

Max Activating Token Index: 450

Text #15

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1178663 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0396. Min Act: -0.0001

Data Index: 234012 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0344. Min Act: -0.0001

Data Index: 291714 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0377. Min Act: -0.0000

Data Index: 248673 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0425. Min Act: -0.0000

Data Index: 699893 (C4 (Web Text))

Max Activating Token Index: 819