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

Dataset: The Pile

Neuron 1272 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: 5.8010. Min Range: -5.8010

Max Act: 5.8010. Min Act: -0.0000

Data Index: 774415 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 5.8010. Min Range: -5.8010

Max Act: 5.5849. Min Act: -0.0000

Data Index: 106589 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 5.8010. Min Range: -5.8010

Max Act: 5.3982. Min Act: -0.0000

Data Index: 1863221 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.7534. Min Act: -0.0000

Data Index: 319392 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.9044. Min Act: -0.0000

Data Index: 1043689 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 5.8010. Min Range: -5.8010

Max Act: 5.0360. Min Act: -0.0000

Data Index: 1439104 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.6657. Min Act: -0.0000

Data Index: 89122 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.5813. Min Act: -0.0000

Data Index: 736758 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.7679. Min Act: -0.0000

Data Index: 1880482 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.8376. Min Act: -0.0000

Data Index: 1808252 (The Pile)

Max Activating Token Index: 910

Text #10

Max Range: 5.8010. Min Range: -5.8010

Max Act: 5.0369. Min Act: -0.0000

Data Index: 557810 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.4494. Min Act: -0.0000

Data Index: 385402 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 5.8010. Min Range: -5.8010

Max Act: 3.7549. Min Act: -0.0000

Data Index: 1319431 (The Pile)

Max Activating Token Index: 984

Text #13

Max Range: 5.8010. Min Range: -5.8010

Max Act: 3.8072. Min Act: -0.0000

Data Index: 1667112 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.1252. Min Act: -0.0000

Data Index: 1497836 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.1525. Min Act: -0.0000

Data Index: 1226152 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.2406. Min Act: -0.0000

Data Index: 1125167 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.0142. Min Act: -0.0000

Data Index: 1282380 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 5.8010. Min Range: -5.8010

Max Act: 3.9770. Min Act: -0.0000

Data Index: 33401 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 5.8010. Min Range: -5.8010

Max Act: 4.3293. Min Act: -0.0000

Data Index: 1256367 (The Pile)

Max Activating Token Index: 817