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

Dataset: The Pile

Neuron 3717 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: 0.4460. Min Range: -0.4460

Max Act: 0.4460. Min Act: -0.0000

Data Index: 315206 (The Pile)

Max Activating Token Index: 216

Text #1

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1370591 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1883235 (The Pile)

Max Activating Token Index: 273

Text #3

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1976115 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1362239 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3880. Min Act: -0.0000

Data Index: 537310 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1302362 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1966443 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1766631 (The Pile)

Max Activating Token Index: 806

Text #9

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3762. Min Act: -0.0000

Data Index: 290258 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1350068 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1856384 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1311114 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1945228 (The Pile)

Max Activating Token Index: 681

Text #14

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1063518 (The Pile)

Max Activating Token Index: 749

Text #15

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3837. Min Act: -0.0000

Data Index: 884694 (The Pile)

Max Activating Token Index: 689

Text #16

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1015894 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3674. Min Act: -0.0000

Data Index: 281731 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1089768 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1618416 (The Pile)

Max Activating Token Index: 288