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

Dataset: The Pile

Neuron 914 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5466. Min Range: -3.5466

Max Act: 3.5380. Min Act: -0.0000

Data Index: 1869523 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 3.5466. Min Range: -3.5466

Max Act: 3.5466. Min Act: -0.0000

Data Index: 965333 (The Pile)

Max Activating Token Index: 589

Text #2

Max Range: 3.5466. Min Range: -3.5466

Max Act: 3.1935. Min Act: -0.0000

Data Index: 916717 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 3.5466. Min Range: -3.5466

Max Act: 3.2406. Min Act: -0.0000

Data Index: 1058060 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 3.5466. Min Range: -3.5466

Max Act: 3.2827. Min Act: -0.0000

Data Index: 1911837 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 3.5466. Min Range: -3.5466

Max Act: 3.2539. Min Act: -0.0000

Data Index: 1333431 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 3.5466. Min Range: -3.5466

Max Act: 3.0118. Min Act: -0.0000

Data Index: 1154193 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 3.5466. Min Range: -3.5466

Max Act: 3.2499. Min Act: -0.0000

Data Index: 415995 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 3.5466. Min Range: -3.5466

Max Act: 2.7834. Min Act: -0.0000

Data Index: 106530 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 3.5466. Min Range: -3.5466

Max Act: 2.6795. Min Act: -0.0000

Data Index: 1741919 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 3.5466. Min Range: -3.5466

Max Act: 2.9535. Min Act: -0.0000

Data Index: 749387 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 3.5466. Min Range: -3.5466

Max Act: 2.6309. Min Act: -0.0000

Data Index: 1194735 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 3.5466. Min Range: -3.5466

Max Act: 3.0185. Min Act: -0.0000

Data Index: 72665 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 3.5466. Min Range: -3.5466

Max Act: 2.9988. Min Act: -0.0000

Data Index: 318926 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 3.5466. Min Range: -3.5466

Max Act: 2.8257. Min Act: -0.0000

Data Index: 303979 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 3.5466. Min Range: -3.5466

Max Act: 2.3671. Min Act: -0.0000

Data Index: 342493 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 3.5466. Min Range: -3.5466

Max Act: 2.8779. Min Act: -0.0000

Data Index: 1949361 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 3.5466. Min Range: -3.5466

Max Act: 3.0375. Min Act: -0.0000

Data Index: 1886135 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 3.5466. Min Range: -3.5466

Max Act: 2.6247. Min Act: -0.0000

Data Index: 684497 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 3.5466. Min Range: -3.5466

Max Act: 2.7028. Min Act: -0.0000

Data Index: 1965335 (The Pile)

Max Activating Token Index: 282