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

Dataset: The Pile

Neuron 1722 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3719. Min Act: -0.0000

Data Index: 338137 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3818. Min Act: -0.0000

Data Index: 649233 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3437. Min Act: -0.0000

Data Index: 365936 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3272. Min Act: -0.0000

Data Index: 283827 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1699219 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1235069 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3133. Min Act: -0.0000

Data Index: 573533 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3071. Min Act: -0.0000

Data Index: 933210 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3226. Min Act: -0.0000

Data Index: 296199 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3287. Min Act: -0.0000

Data Index: 69589 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2785. Min Act: 0.0000

Data Index: 1170301 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1362758 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2972. Min Act: -0.0000

Data Index: 131650 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2748. Min Act: 0.0000

Data Index: 374776 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1518069 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1968333 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2362. Min Act: 0.0000

Data Index: 978427 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1158003 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2731. Min Act: 0.0000

Data Index: 920848 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1331654 (The Pile)

Max Activating Token Index: 795