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

Dataset: The Pile

Neuron 2683 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: 5.8120. Min Range: -5.8120

Max Act: 5.8120. Min Act: -0.0000

Data Index: 1756473 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.5374. Min Act: -0.0000

Data Index: 1198641 (The Pile)

Max Activating Token Index: 247

Text #2

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.6693. Min Act: -0.0000

Data Index: 80707 (The Pile)

Max Activating Token Index: 19

Text #3

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.1519. Min Act: -0.0000

Data Index: 722945 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.5031. Min Act: -0.0000

Data Index: 1215919 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.2712. Min Act: -0.0000

Data Index: 137957 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.2670. Min Act: -0.0000

Data Index: 109644 (The Pile)

Max Activating Token Index: 933

Text #7

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.0746. Min Act: -0.0000

Data Index: 552262 (The Pile)

Max Activating Token Index: 810

Text #8

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.1933. Min Act: -0.0000

Data Index: 1454600 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 5.8120. Min Range: -5.8120

Max Act: 4.8000. Min Act: -0.0000

Data Index: 50520 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.1538. Min Act: -0.0000

Data Index: 925763 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 5.8120. Min Range: -5.8120

Max Act: 4.6057. Min Act: -0.0000

Data Index: 1827652 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 5.8120. Min Range: -5.8120

Max Act: 4.7702. Min Act: -0.0000

Data Index: 1863298 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 5.8120. Min Range: -5.8120

Max Act: 4.9043. Min Act: -0.0000

Data Index: 1529152 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 5.8120. Min Range: -5.8120

Max Act: 4.6896. Min Act: -0.0000

Data Index: 1099432 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.0548. Min Act: -0.0000

Data Index: 1343790 (The Pile)

Max Activating Token Index: 524

Text #16

Max Range: 5.8120. Min Range: -5.8120

Max Act: 4.8688. Min Act: -0.0000

Data Index: 1568634 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 5.8120. Min Range: -5.8120

Max Act: 4.6526. Min Act: -0.0000

Data Index: 84193 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 5.8120. Min Range: -5.8120

Max Act: 4.6725. Min Act: -0.0000

Data Index: 1832191 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.0173. Min Act: -0.0000

Data Index: 820318 (The Pile)

Max Activating Token Index: 57