Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4229 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.4177. Min Act: -0.0000

Data Index: 960499 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1903508 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3555. Min Act: -0.0000

Data Index: 1756596 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3515. Min Act: -0.0000

Data Index: 839663 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3355. Min Act: -0.0000

Data Index: 1370149 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2891. Min Act: -0.0000

Data Index: 707886 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2589. Min Act: -0.0000

Data Index: 307707 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2502. Min Act: -0.0000

Data Index: 528836 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2091. Min Act: -0.0000

Data Index: 494542 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2410. Min Act: -0.0000

Data Index: 28263 (The Pile)

Max Activating Token Index: 296

Text #10

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2413. Min Act: -0.0000

Data Index: 607886 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2400. Min Act: -0.0000

Data Index: 499844 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1202394 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2193. Min Act: -0.0000

Data Index: 1648654 (The Pile)

Max Activating Token Index: 395

Text #14

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1449882 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1789. Min Act: -0.0000

Data Index: 207270 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1757. Min Act: -0.0000

Data Index: 1903783 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1269. Min Act: -0.0000

Data Index: 40562 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1333. Min Act: -0.0000

Data Index: 95448 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1557. Min Act: -0.0000

Data Index: 295964 (The Pile)

Max Activating Token Index: 478