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

Dataset: The Pile

Neuron 1695 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: 1.2232. Min Range: -1.2232

Max Act: 1.2232. Min Act: -0.0000

Data Index: 604761 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1782329 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.8346. Min Act: -0.0000

Data Index: 550284 (The Pile)

Max Activating Token Index: 720

Text #3

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.7631. Min Act: -0.0000

Data Index: 363389 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.7611. Min Act: -0.0000

Data Index: 1624101 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1745867 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.6481. Min Act: -0.0000

Data Index: 870280 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.6546. Min Act: -0.0000

Data Index: 120115 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1745259 (The Pile)

Max Activating Token Index: 434

Text #9

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.6200. Min Act: -0.0000

Data Index: 310162 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1202627 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1875194 (The Pile)

Max Activating Token Index: 608

Text #12

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.6020. Min Act: -0.0000

Data Index: 720915 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1686940 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1431188 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1653004 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1623795 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1157396 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1276378 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 1.2232. Min Range: -1.2232

Max Act: 0.6286. Min Act: -0.0000

Data Index: 699140 (The Pile)

Max Activating Token Index: 748