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

Dataset: The Pile

Neuron 2407 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: 0.7885. Min Range: -0.7885

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1798459 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.7213. Min Act: -0.0000

Data Index: 566495 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1514459 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1423795 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.6519. Min Act: -0.0000

Data Index: 98027 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5979. Min Act: -0.0000

Data Index: 621313 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1530355 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1472160 (The Pile)

Max Activating Token Index: 426

Text #8

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1155612 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5424. Min Act: -0.0000

Data Index: 12954 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1720639 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5480. Min Act: -0.0000

Data Index: 971425 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5087. Min Act: -0.0000

Data Index: 300381 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5186. Min Act: -0.0000

Data Index: 370817 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4805. Min Act: -0.0000

Data Index: 291552 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1975681 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5145. Min Act: -0.0000

Data Index: 645750 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5108. Min Act: -0.0000

Data Index: 350231 (The Pile)

Max Activating Token Index: 605

Text #18

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1211687 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1732961 (The Pile)

Max Activating Token Index: 968