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

Dataset: The Pile

Neuron 4505 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: 0.8555. Min Range: -0.8555

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1684781 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7300. Min Act: -0.0000

Data Index: 179825 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1610433 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7830. Min Act: -0.0000

Data Index: 701937 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1607749 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1035110 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7263. Min Act: -0.0000

Data Index: 387872 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1077024 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7034. Min Act: -0.0000

Data Index: 556111 (The Pile)

Max Activating Token Index: 54

Text #9

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6672. Min Act: -0.0000

Data Index: 231563 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1561570 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6686. Min Act: -0.0000

Data Index: 146047 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1270029 (The Pile)

Max Activating Token Index: 873

Text #13

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1740441 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1924865 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6698. Min Act: -0.0000

Data Index: 486347 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.7023. Min Act: -0.0000

Data Index: 704840 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1519049 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6295. Min Act: -0.0000

Data Index: 530478 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 0.8555. Min Range: -0.8555

Max Act: 0.6133. Min Act: -0.0000

Data Index: 93142 (The Pile)

Max Activating Token Index: 184