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

Dataset: The Pile

Neuron 2722 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.9369. Min Act: -0.0000

Data Index: 739637 (The Pile)

Max Activating Token Index: 676

Text #1

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.5700. Min Act: -0.0000

Data Index: 1290820 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.7243. Min Act: -0.0000

Data Index: 770525 (The Pile)

Max Activating Token Index: 847

Text #3

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.5354. Min Act: -0.0000

Data Index: 459204 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.5823. Min Act: -0.0000

Data Index: 956690 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.4487. Min Act: -0.0000

Data Index: 1474520 (The Pile)

Max Activating Token Index: 839

Text #6

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.4658. Min Act: -0.0000

Data Index: 751971 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.4269. Min Act: -0.0000

Data Index: 1305104 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.4615. Min Act: -0.0000

Data Index: 190241 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.4914. Min Act: -0.0000

Data Index: 58223 (The Pile)

Max Activating Token Index: 607

Text #10

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.4218. Min Act: -0.0000

Data Index: 1235962 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.1917. Min Act: -0.0000

Data Index: 727880 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1064878 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.2801. Min Act: -0.0000

Data Index: 1243925 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.3108. Min Act: -0.0000

Data Index: 997845 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.2882. Min Act: -0.0000

Data Index: 630147 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1521249 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.3129. Min Act: -0.0000

Data Index: 379689 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.2657. Min Act: -0.0000

Data Index: 442817 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 1.9369. Min Range: -1.9369

Max Act: 1.3397. Min Act: -0.0000

Data Index: 291466 (The Pile)

Max Activating Token Index: 837