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

Dataset: The Pile

Neuron 4100 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0906. Min Range: -3.0906

Max Act: 3.0906. Min Act: -0.0000

Data Index: 988434 (The Pile)

Max Activating Token Index: 252

Text #1

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.7936. Min Act: -0.0000

Data Index: 373490 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.5612. Min Act: 0.0000

Data Index: 191591 (The Pile)

Max Activating Token Index: 99

Text #3

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.5237. Min Act: 0.0000

Data Index: 1201753 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.5971. Min Act: 0.0000

Data Index: 962033 (The Pile)

Max Activating Token Index: 45

Text #5

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.3848. Min Act: -0.0000

Data Index: 1824917 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1025403 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.4343. Min Act: 0.0000

Data Index: 1764815 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.3878. Min Act: -0.0000

Data Index: 445520 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1528216 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.3332. Min Act: -0.0000

Data Index: 1777991 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1102808 (The Pile)

Max Activating Token Index: 1019

Text #12

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1925953 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.3977. Min Act: -0.0000

Data Index: 138257 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.1779. Min Act: 0.0000

Data Index: 1769629 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.2926. Min Act: -0.0000

Data Index: 259244 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.3831. Min Act: -0.0000

Data Index: 363525 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.2835. Min Act: 0.0000

Data Index: 1257260 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.3529. Min Act: -0.0000

Data Index: 1004807 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 3.0906. Min Range: -3.0906

Max Act: 1.3622. Min Act: -0.0000

Data Index: 530617 (The Pile)

Max Activating Token Index: 973