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

Dataset: The Pile

Neuron 1155 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: 0.6063. Min Range: -0.6063

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1075971 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4855. Min Act: -0.0000

Data Index: 961645 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1988075 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4456. Min Act: -0.0000

Data Index: 734708 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4241. Min Act: -0.0000

Data Index: 539524 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1515472 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4690. Min Act: -0.0000

Data Index: 275959 (The Pile)

Max Activating Token Index: 711

Text #7

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3967. Min Act: -0.0000

Data Index: 451371 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3744. Min Act: -0.0000

Data Index: 963523 (The Pile)

Max Activating Token Index: 770

Text #9

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3895. Min Act: -0.0000

Data Index: 886082 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1598641 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3412. Min Act: -0.0000

Data Index: 339099 (The Pile)

Max Activating Token Index: 713

Text #12

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3500. Min Act: -0.0000

Data Index: 123097 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1630330 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1629143 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1723115 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1980083 (The Pile)

Max Activating Token Index: 412

Text #17

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3618. Min Act: -0.0000

Data Index: 648778 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3357. Min Act: -0.0000

Data Index: 425346 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1827211 (The Pile)

Max Activating Token Index: 779