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

Dataset: The Pile

Neuron 3050 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.5177. Min Act: -0.0000

Data Index: 495015 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1193454 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4473. Min Act: -0.0000

Data Index: 319706 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1405202 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4466. Min Act: -0.0000

Data Index: 760096 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1500211 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1722684 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1038936 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4381. Min Act: -0.0000

Data Index: 188357 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4202. Min Act: -0.0000

Data Index: 807647 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1474621 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1349592 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1453503 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1486712 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4278. Min Act: -0.0000

Data Index: 565514 (The Pile)

Max Activating Token Index: 199

Text #15

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1372490 (The Pile)

Max Activating Token Index: 653

Text #16

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1873430 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4202. Min Act: -0.0000

Data Index: 359913 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4299. Min Act: -0.0000

Data Index: 228818 (The Pile)

Max Activating Token Index: 389

Text #19

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1961993 (The Pile)

Max Activating Token Index: 884