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

Dataset: The Pile

Neuron 4523 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: 0.5444. Min Range: -0.5444

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1521941 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1854016 (The Pile)

Max Activating Token Index: 375

Text #2

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4977. Min Act: -0.0000

Data Index: 869814 (The Pile)

Max Activating Token Index: 116

Text #3

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.5211. Min Act: -0.0000

Data Index: 699514 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4827. Min Act: -0.0000

Data Index: 749683 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4975. Min Act: -0.0000

Data Index: 927554 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4136. Min Act: -0.0000

Data Index: 566445 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4245. Min Act: -0.0000

Data Index: 662400 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.4125. Min Act: -0.0000

Data Index: 993190 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1349316 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3839. Min Act: -0.0000

Data Index: 371468 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1662356 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3804. Min Act: -0.0000

Data Index: 825588 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1062830 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3710. Min Act: -0.0000

Data Index: 192229 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1689552 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1520591 (The Pile)

Max Activating Token Index: 621

Text #17

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1750055 (The Pile)

Max Activating Token Index: 585

Text #18

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1377336 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 0.5444. Min Range: -0.5444

Max Act: 0.3766. Min Act: -0.0000

Data Index: 458677 (The Pile)

Max Activating Token Index: 663