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

Dataset: The Pile

Neuron 3252 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: 1.7615. Min Range: -1.7615

Max Act: 1.7577. Min Act: -0.0000

Data Index: 1982235 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7516. Min Act: -0.0000

Data Index: 1768361 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7490. Min Act: -0.0000

Data Index: 617879 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1906255 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7615. Min Act: -0.0000

Data Index: 1745367 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6986. Min Act: -0.0000

Data Index: 1807193 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6779. Min Act: -0.0000

Data Index: 1171472 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7323. Min Act: -0.0000

Data Index: 452804 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6693. Min Act: -0.0000

Data Index: 99806 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6189. Min Act: -0.0000

Data Index: 1826849 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6325. Min Act: -0.0000

Data Index: 466861 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6476. Min Act: -0.0000

Data Index: 189389 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6335. Min Act: -0.0000

Data Index: 510773 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5739. Min Act: -0.0000

Data Index: 1910842 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5557. Min Act: -0.0000

Data Index: 1733461 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6269. Min Act: -0.0000

Data Index: 365052 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5992. Min Act: -0.0000

Data Index: 1679701 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5422. Min Act: -0.0000

Data Index: 1936406 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5834. Min Act: -0.0000

Data Index: 1640982 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6251. Min Act: -0.0000

Data Index: 212849 (The Pile)

Max Activating Token Index: 901