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

Dataset: The Pile

Neuron 1107 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: 0.5293. Min Range: -0.5293

Max Act: 0.5293. Min Act: -0.0000

Data Index: 44648 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.5214. Min Act: -0.0000

Data Index: 324994 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1788862 (The Pile)

Max Activating Token Index: 952

Text #3

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1197380 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3815. Min Act: -0.0000

Data Index: 847982 (The Pile)

Max Activating Token Index: 779

Text #5

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3718. Min Act: -0.0000

Data Index: 667524 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3879. Min Act: -0.0000

Data Index: 948893 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1152322 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3742. Min Act: -0.0000

Data Index: 902855 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1848463 (The Pile)

Max Activating Token Index: 480

Text #10

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1144371 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3424. Min Act: -0.0000

Data Index: 819055 (The Pile)

Max Activating Token Index: 792

Text #12

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3230. Min Act: -0.0000

Data Index: 595189 (The Pile)

Max Activating Token Index: 863

Text #13

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1680133 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.2919. Min Act: -0.0000

Data Index: 114461 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1691911 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.2951. Min Act: -0.0000

Data Index: 564951 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3011. Min Act: -0.0000

Data Index: 168336 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.2793. Min Act: -0.0000

Data Index: 74418 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.2802. Min Act: -0.0000

Data Index: 364818 (The Pile)

Max Activating Token Index: 917