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

Dataset: The Pile

Neuron 4392 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0909. Min Act: -0.0000

Data Index: 922494 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0878. Min Act: -0.0000

Data Index: 115040 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0822. Min Act: -0.0000

Data Index: 246540 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0783. Min Act: -0.0000

Data Index: 1482044 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1632800 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0878. Min Act: -0.0000

Data Index: 478123 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0873. Min Act: -0.0000

Data Index: 629990 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0764. Min Act: -0.0000

Data Index: 1552938 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1453026 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0706. Min Act: -0.0000

Data Index: 885878 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1309751 (The Pile)

Max Activating Token Index: 337

Text #11

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0772. Min Act: -0.0000

Data Index: 338021 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0795. Min Act: -0.0000

Data Index: 435129 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0757. Min Act: -0.0000

Data Index: 463631 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0731. Min Act: -0.0000

Data Index: 600852 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0673. Min Act: -0.0000

Data Index: 176504 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0682. Min Act: -0.0000

Data Index: 908018 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0819. Min Act: -0.0000

Data Index: 226235 (The Pile)

Max Activating Token Index: 774

Text #18

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1468129 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1859676 (The Pile)

Max Activating Token Index: 598