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

Dataset: The Pile

Neuron 1110 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: 0.5485. Min Range: -0.5485

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1020019 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1073192 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.5038. Min Act: -0.0000

Data Index: 353257 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.5245. Min Act: -0.0000

Data Index: 393960 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4701. Min Act: 0.0000

Data Index: 579811 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1587757 (The Pile)

Max Activating Token Index: 87

Text #6

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1073896 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4517. Min Act: -0.0000

Data Index: 11833 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4324. Min Act: -0.0000

Data Index: 217674 (The Pile)

Max Activating Token Index: 781

Text #9

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4175. Min Act: 0.0001

Data Index: 604428 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4195. Min Act: -0.0000

Data Index: 344917 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3779. Min Act: 0.0000

Data Index: 169273 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4115. Min Act: -0.0000

Data Index: 761559 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1595576 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1797502 (The Pile)

Max Activating Token Index: 529

Text #15

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3704. Min Act: -0.0000

Data Index: 843348 (The Pile)

Max Activating Token Index: 328

Text #16

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1695942 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3604. Min Act: -0.0000

Data Index: 946013 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3445. Min Act: 0.0000

Data Index: 1747410 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1641422 (The Pile)

Max Activating Token Index: 54