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

Dataset: The Pile

Neuron 3806 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: 0.9638. Min Range: -0.9638

Max Act: 0.9638. Min Act: -0.0000

Data Index: 843650 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8668. Min Act: -0.0000

Data Index: 422785 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7740. Min Act: -0.0000

Data Index: 915294 (The Pile)

Max Activating Token Index: 724

Text #3

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7674. Min Act: -0.0000

Data Index: 55771 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7748. Min Act: -0.0000

Data Index: 561142 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7942. Min Act: -0.0000

Data Index: 609724 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7903. Min Act: -0.0000

Data Index: 178933 (The Pile)

Max Activating Token Index: 521

Text #7

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1681400 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7522. Min Act: -0.0000

Data Index: 24817 (The Pile)

Max Activating Token Index: 401

Text #9

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1016155 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1856243 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1082739 (The Pile)

Max Activating Token Index: 452

Text #12

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6882. Min Act: -0.0000

Data Index: 376049 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6891. Min Act: -0.0000

Data Index: 434153 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6277. Min Act: -0.0000

Data Index: 161767 (The Pile)

Max Activating Token Index: 799

Text #15

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6518. Min Act: -0.0000

Data Index: 645890 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1528029 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1106585 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1018316 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6829. Min Act: -0.0000

Data Index: 905797 (The Pile)

Max Activating Token Index: 178