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

Dataset: The Pile

Neuron 2578 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: 0.6648. Min Range: -0.6648

Max Act: 0.6648. Min Act: -0.0000

Data Index: 710965 (The Pile)

Max Activating Token Index: 601

Text #1

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1929891 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5746. Min Act: -0.0000

Data Index: 43261 (The Pile)

Max Activating Token Index: 635

Text #3

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1382375 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1057631 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5834. Min Act: 0.0000

Data Index: 1444154 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1428868 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1045334 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5115. Min Act: -0.0000

Data Index: 302273 (The Pile)

Max Activating Token Index: 32

Text #9

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5405. Min Act: -0.0000

Data Index: 10483 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1444696 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1178997 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5056. Min Act: -0.0000

Data Index: 24317 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4463. Min Act: -0.0000

Data Index: 433385 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4988. Min Act: -0.0000

Data Index: 135649 (The Pile)

Max Activating Token Index: 721

Text #15

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4615. Min Act: -0.0000

Data Index: 380681 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1954800 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5071. Min Act: -0.0000

Data Index: 508978 (The Pile)

Max Activating Token Index: 214

Text #18

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1236235 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1295827 (The Pile)

Max Activating Token Index: 138