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

Dataset: The Pile

Neuron 1650 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1448212 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.7623. Min Act: -0.0000

Data Index: 421735 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1442529 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.5327. Min Act: -0.0000

Data Index: 506464 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1524200 (The Pile)

Max Activating Token Index: 164

Text #5

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.4695. Min Act: -0.0000

Data Index: 635503 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1705963 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.4215. Min Act: -0.0000

Data Index: 292936 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.4209. Min Act: -0.0000

Data Index: 811729 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.4299. Min Act: -0.0000

Data Index: 817394 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3744. Min Act: -0.0000

Data Index: 942379 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1212606 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1874261 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1375258 (The Pile)

Max Activating Token Index: 192

Text #14

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1476522 (The Pile)

Max Activating Token Index: 308

Text #15

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1539489 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1356190 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3406. Min Act: -0.0000

Data Index: 636022 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3401. Min Act: -0.0000

Data Index: 499717 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 0.7623. Min Range: -0.7623

Max Act: 0.3357. Min Act: -0.0000

Data Index: 262345 (The Pile)

Max Activating Token Index: 847