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

Dataset: The Pile

Neuron 4371 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: 0.9815. Min Range: -0.9815

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1948178 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1672539 (The Pile)

Max Activating Token Index: 221

Text #2

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8718. Min Act: -0.0000

Data Index: 753769 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.9247. Min Act: -0.0000

Data Index: 712544 (The Pile)

Max Activating Token Index: 328

Text #4

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1190753 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8483. Min Act: -0.0000

Data Index: 719815 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7848. Min Act: -0.0000

Data Index: 648626 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8122. Min Act: -0.0000

Data Index: 984704 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7720. Min Act: -0.0000

Data Index: 833266 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7296. Min Act: -0.0000

Data Index: 132401 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7851. Min Act: -0.0000

Data Index: 205157 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7793. Min Act: -0.0000

Data Index: 589165 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7780. Min Act: -0.0000

Data Index: 239379 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7733. Min Act: -0.0000

Data Index: 750347 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1050684 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1778584 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7544. Min Act: 0.0001

Data Index: 1858471 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7088. Min Act: -0.0000

Data Index: 951263 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7269. Min Act: -0.0000

Data Index: 353018 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.6978. Min Act: -0.0000

Data Index: 42886 (The Pile)

Max Activating Token Index: 70