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

Dataset: The Pile

Neuron 2494 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: 5.9333. Min Range: -5.9333

Max Act: 5.9333. Min Act: -0.0000

Data Index: 695993 (The Pile)

Max Activating Token Index: 869

Text #1

Max Range: 5.9333. Min Range: -5.9333

Max Act: 5.3852. Min Act: -0.0000

Data Index: 1566398 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.8941. Min Act: -0.0000

Data Index: 1889152 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.6409. Min Act: -0.0000

Data Index: 1292994 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.7366. Min Act: -0.0000

Data Index: 1477028 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 5.9333. Min Range: -5.9333

Max Act: 4.1057. Min Act: -0.0000

Data Index: 71072 (The Pile)

Max Activating Token Index: 669

Text #6

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.3557. Min Act: -0.0000

Data Index: 519327 (The Pile)

Max Activating Token Index: 728

Text #7

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.7813. Min Act: -0.0000

Data Index: 148914 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.6271. Min Act: 0.0000

Data Index: 128637 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.5269. Min Act: -0.0000

Data Index: 1842570 (The Pile)

Max Activating Token Index: 465

Text #10

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.6910. Min Act: -0.0000

Data Index: 1820815 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.5005. Min Act: -0.0000

Data Index: 1932379 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.1518. Min Act: -0.0000

Data Index: 1516510 (The Pile)

Max Activating Token Index: 531

Text #13

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.1744. Min Act: -0.0000

Data Index: 297789 (The Pile)

Max Activating Token Index: 502

Text #14

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.3177. Min Act: -0.0000

Data Index: 136017 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.6796. Min Act: -0.0000

Data Index: 1958601 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.4787. Min Act: -0.0000

Data Index: 895512 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.1642. Min Act: -0.0000

Data Index: 562380 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.4087. Min Act: -0.0000

Data Index: 210697 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 5.9333. Min Range: -5.9333

Max Act: 3.5233. Min Act: -0.0000

Data Index: 1683253 (The Pile)

Max Activating Token Index: 559