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

Dataset: The Pile

Neuron 3277 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3612. Min Act: -0.0000

Data Index: 548536 (The Pile)

Max Activating Token Index: 924

Text #1

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1548721 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1686379 (The Pile)

Max Activating Token Index: 188

Text #3

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1483966 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1112772 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3569. Min Act: -0.0000

Data Index: 174821 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1994921 (The Pile)

Max Activating Token Index: 569

Text #7

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1245604 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1834707 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3532. Min Act: -0.0000

Data Index: 649064 (The Pile)

Max Activating Token Index: 204

Text #10

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1652990 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1426591 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3178. Min Act: -0.0000

Data Index: 627082 (The Pile)

Max Activating Token Index: 873

Text #13

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3528. Min Act: -0.0000

Data Index: 619895 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1717484 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1485781 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3101. Min Act: -0.0000

Data Index: 582465 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.2980. Min Act: -0.0000

Data Index: 623996 (The Pile)

Max Activating Token Index: 642

Text #18

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1150138 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1867168 (The Pile)

Max Activating Token Index: 300