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

Dataset: The Pile

Neuron 552 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1713. Min Range: -1.1713

Max Act: 1.1713. Min Act: -0.0000

Data Index: 1006009 (The Pile)

Max Activating Token Index: 734

Text #1

Max Range: 1.1713. Min Range: -1.1713

Max Act: 1.0749. Min Act: -0.0000

Data Index: 151693 (The Pile)

Max Activating Token Index: 807

Text #2

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.9786. Min Act: -0.0000

Data Index: 249150 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8451. Min Act: -0.0000

Data Index: 112352 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7919. Min Act: -0.0000

Data Index: 635556 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1788371 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8252. Min Act: -0.0000

Data Index: 603166 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7940. Min Act: -0.0000

Data Index: 928438 (The Pile)

Max Activating Token Index: 248

Text #8

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1111202 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1100656 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1745502 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7946. Min Act: 0.0000

Data Index: 1328670 (The Pile)

Max Activating Token Index: 708

Text #12

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1561876 (The Pile)

Max Activating Token Index: 413

Text #13

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7164. Min Act: 0.0000

Data Index: 1872079 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1852563 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.6986. Min Act: -0.0000

Data Index: 14227 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.6967. Min Act: -0.0000

Data Index: 762959 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.6855. Min Act: 0.0000

Data Index: 1514880 (The Pile)

Max Activating Token Index: 364

Text #18

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.6769. Min Act: -0.0000

Data Index: 720780 (The Pile)

Max Activating Token Index: 685

Text #19

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.6642. Min Act: -0.0000

Data Index: 290801 (The Pile)

Max Activating Token Index: 824