Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1746 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 4.2560. Min Range: -4.2560

Max Act: 4.2560. Min Act: -0.0000

Data Index: 1903414 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.6040. Min Act: -0.0000

Data Index: 176062 (The Pile)

Max Activating Token Index: 630

Text #2

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.6892. Min Act: -0.0000

Data Index: 1179091 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.4730. Min Act: -0.0000

Data Index: 700558 (The Pile)

Max Activating Token Index: 506

Text #4

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.5461. Min Act: -0.0000

Data Index: 1026141 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.5192. Min Act: -0.0000

Data Index: 353856 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.4791. Min Act: -0.0000

Data Index: 1203873 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.4434. Min Act: -0.0000

Data Index: 1732022 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.1698. Min Act: -0.0000

Data Index: 1960177 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.3191. Min Act: -0.0000

Data Index: 1721819 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.7786. Min Act: -0.0000

Data Index: 461160 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.3114. Min Act: -0.0000

Data Index: 1797867 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.0023. Min Act: -0.0000

Data Index: 1283367 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.2478. Min Act: -0.0000

Data Index: 1306144 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 4.2560. Min Range: -4.2560

Max Act: 2.9977. Min Act: -0.0000

Data Index: 320167 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.0858. Min Act: -0.0000

Data Index: 904793 (The Pile)

Max Activating Token Index: 24

Text #16

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.1813. Min Act: -0.0000

Data Index: 406510 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.3142. Min Act: -0.0000

Data Index: 439093 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 4.2560. Min Range: -4.2560

Max Act: 3.1591. Min Act: -0.0000

Data Index: 1762859 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 4.2560. Min Range: -4.2560

Max Act: 2.8407. Min Act: -0.0000

Data Index: 1527883 (The Pile)

Max Activating Token Index: 945