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

Dataset: The Pile

Neuron 490 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: 0.6707. Min Range: -0.6707

Max Act: 0.6707. Min Act: -0.0000

Data Index: 644771 (The Pile)

Max Activating Token Index: 379

Text #1

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5960. Min Act: -0.0000

Data Index: 352989 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5316. Min Act: -0.0000

Data Index: 794484 (The Pile)

Max Activating Token Index: 487

Text #3

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1234568 (The Pile)

Max Activating Token Index: 889

Text #4

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1948205 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1838952 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.5249. Min Act: -0.0000

Data Index: 823096 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1675700 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4526. Min Act: -0.0000

Data Index: 812621 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1386929 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4426. Min Act: -0.0000

Data Index: 887213 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1609502 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.3960. Min Act: -0.0000

Data Index: 749060 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4306. Min Act: -0.0000

Data Index: 591665 (The Pile)

Max Activating Token Index: 251

Text #14

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4440. Min Act: -0.0000

Data Index: 431271 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4133. Min Act: -0.0000

Data Index: 718121 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.3923. Min Act: -0.0000

Data Index: 631026 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1333928 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1419194 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 0.6707. Min Range: -0.6707

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1221470 (The Pile)

Max Activating Token Index: 770