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

Dataset: The Pile

Neuron 2122 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: 0.5666. Min Range: -0.5666

Max Act: 0.5666. Min Act: -0.0000

Data Index: 57500 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1461731 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4191. Min Act: -0.0000

Data Index: 215797 (The Pile)

Max Activating Token Index: 949

Text #3

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1847092 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1719544 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4195. Min Act: -0.0000

Data Index: 211971 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1027800 (The Pile)

Max Activating Token Index: 805

Text #7

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1042662 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4072. Min Act: -0.0000

Data Index: 722117 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4350. Min Act: -0.0000

Data Index: 745302 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3675. Min Act: -0.0000

Data Index: 247397 (The Pile)

Max Activating Token Index: 761

Text #11

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1067042 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1027300 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1987260 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1809071 (The Pile)

Max Activating Token Index: 481

Text #15

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3452. Min Act: -0.0000

Data Index: 363153 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3751. Min Act: -0.0000

Data Index: 679313 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3389. Min Act: -0.0000

Data Index: 163929 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1123433 (The Pile)

Max Activating Token Index: 898

Text #19

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1133098 (The Pile)

Max Activating Token Index: 543