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

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

Neuron 1198 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.5565. Min Act: -0.0000

Data Index: 205520 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4301. Min Act: -0.0000

Data Index: 265295 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4290. Min Act: -0.0001

Data Index: 243409 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4202. Min Act: -0.0001

Data Index: 35076 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3883. Min Act: -0.0000

Data Index: 616434 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3975. Min Act: -0.0001

Data Index: 786603 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3722. Min Act: -0.0000

Data Index: 989982 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1037434 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3387. Min Act: -0.0001

Data Index: 1367386 (Python Code)

Max Activating Token Index: 728

Text #9

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3425. Min Act: -0.0001

Data Index: 941551 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3255. Min Act: -0.0001

Data Index: 365259 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3218. Min Act: -0.0001

Data Index: 43660 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3189. Min Act: -0.0000

Data Index: 874234 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3285. Min Act: -0.0001

Data Index: 784961 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1486742 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1404172 (Python Code)

Max Activating Token Index: 372

Text #16

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3313. Min Act: -0.0001

Data Index: 1608970 (Python Code)

Max Activating Token Index: 961

Text #17

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3179. Min Act: -0.0000

Data Index: 965991 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3150. Min Act: -0.0001

Data Index: 1519437 (Python Code)

Max Activating Token Index: 315

Text #19

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3103. Min Act: -0.0000

Data Index: 977837 (C4 (Web Text))

Max Activating Token Index: 730