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

Dataset: The Pile

Neuron 1436 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: 0.8880. Min Range: -0.8880

Max Act: 0.8477. Min Act: -0.0000

Data Index: 735094 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1709525 (The Pile)

Max Activating Token Index: 434

Text #2

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1163329 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7617. Min Act: -0.0000

Data Index: 660367 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1565916 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7054. Min Act: 0.0000

Data Index: 436934 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6796. Min Act: -0.0000

Data Index: 103453 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6570. Min Act: -0.0000

Data Index: 131731 (The Pile)

Max Activating Token Index: 765

Text #8

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1111620 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6422. Min Act: -0.0000

Data Index: 26666 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6307. Min Act: -0.0000

Data Index: 739222 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1677647 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5836. Min Act: 0.0000

Data Index: 337637 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1416069 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5417. Min Act: -0.0000

Data Index: 367470 (The Pile)

Max Activating Token Index: 672

Text #15

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5940. Min Act: 0.0001

Data Index: 1376312 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6141. Min Act: -0.0000

Data Index: 747615 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5462. Min Act: -0.0000

Data Index: 149078 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5223. Min Act: -0.0000

Data Index: 720458 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1199064 (The Pile)

Max Activating Token Index: 354