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

Dataset: The Pile

Neuron 3375 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: 0.5390. Min Range: -0.5390

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1378889 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.5361. Min Act: -0.0000

Data Index: 232801 (The Pile)

Max Activating Token Index: 39

Text #2

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1994806 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1990393 (The Pile)

Max Activating Token Index: 899

Text #4

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.4493. Min Act: -0.0000

Data Index: 790795 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1772806 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.4057. Min Act: -0.0000

Data Index: 132881 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3914. Min Act: -0.0000

Data Index: 158180 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1487652 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1990546 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.4065. Min Act: -0.0000

Data Index: 780120 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3761. Min Act: -0.0000

Data Index: 638423 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1084320 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1168640 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3920. Min Act: -0.0000

Data Index: 89616 (The Pile)

Max Activating Token Index: 293

Text #15

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1298011 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1164188 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1666067 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3510. Min Act: -0.0000

Data Index: 62079 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 0.5390. Min Range: -0.5390

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1024028 (The Pile)

Max Activating Token Index: 735