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

Dataset: The Pile

Neuron 406 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: 5.5617. Min Range: -5.5617

Max Act: 5.5617. Min Act: -0.0000

Data Index: 622853 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 5.5617. Min Range: -5.5617

Max Act: 5.2232. Min Act: -0.0000

Data Index: 1998007 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 5.5617. Min Range: -5.5617

Max Act: 5.0651. Min Act: -0.0000

Data Index: 1847682 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 5.5617. Min Range: -5.5617

Max Act: 5.3917. Min Act: -0.0000

Data Index: 1711416 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.9483. Min Act: -0.0000

Data Index: 174231 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.7328. Min Act: -0.0000

Data Index: 351205 (The Pile)

Max Activating Token Index: 966

Text #6

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.9573. Min Act: -0.0000

Data Index: 990481 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.4343. Min Act: -0.0000

Data Index: 1410640 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.8103. Min Act: -0.0000

Data Index: 760125 (The Pile)

Max Activating Token Index: 337

Text #9

Max Range: 5.5617. Min Range: -5.5617

Max Act: 5.1405. Min Act: -0.0000

Data Index: 1850965 (The Pile)

Max Activating Token Index: 841

Text #10

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.7300. Min Act: -0.0000

Data Index: 1606123 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.5405. Min Act: -0.0000

Data Index: 1706518 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.7265. Min Act: -0.0000

Data Index: 289220 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 5.5617. Min Range: -5.5617

Max Act: 5.2513. Min Act: -0.0000

Data Index: 191904 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.7019. Min Act: -0.0000

Data Index: 177277 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.8768. Min Act: -0.0000

Data Index: 1137338 (The Pile)

Max Activating Token Index: 545

Text #16

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.8957. Min Act: -0.0000

Data Index: 11360 (The Pile)

Max Activating Token Index: 850

Text #17

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.6595. Min Act: -0.0000

Data Index: 1512795 (The Pile)

Max Activating Token Index: 815

Text #18

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.6304. Min Act: -0.0000

Data Index: 808166 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 5.5617. Min Range: -5.5617

Max Act: 4.5939. Min Act: -0.0000

Data Index: 1092215 (The Pile)

Max Activating Token Index: 530