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

Dataset: The Pile

Neuron 2165 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1390624 (The Pile)

Max Activating Token Index: 366

Text #1

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1960510 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8606. Min Act: -0.0000

Data Index: 256990 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7911. Min Act: -0.0000

Data Index: 63385 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7905. Min Act: -0.0000

Data Index: 907640 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7893. Min Act: -0.0000

Data Index: 364144 (The Pile)

Max Activating Token Index: 234

Text #6

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1061758 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7437. Min Act: -0.0000

Data Index: 703001 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1639063 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1489063 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7079. Min Act: -0.0000

Data Index: 275317 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7289. Min Act: -0.0000

Data Index: 310442 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6460. Min Act: -0.0000

Data Index: 707751 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1495619 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7286. Min Act: -0.0000

Data Index: 427275 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7048. Min Act: -0.0000

Data Index: 545704 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1569384 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1749933 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1102535 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1266877 (The Pile)

Max Activating Token Index: 252