Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1100 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1708630 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1484133 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1671221 (The Pile)

Max Activating Token Index: 535

Text #3

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1804131 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1576528 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6472. Min Act: -0.0000

Data Index: 487423 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1690606 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6621. Min Act: -0.0000

Data Index: 317069 (The Pile)

Max Activating Token Index: 39

Text #8

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1732817 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6636. Min Act: -0.0000

Data Index: 449138 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1269361 (The Pile)

Max Activating Token Index: 217

Text #11

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1584936 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5538. Min Act: -0.0000

Data Index: 933983 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1560892 (The Pile)

Max Activating Token Index: 718

Text #14

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6411. Min Act: -0.0000

Data Index: 768968 (The Pile)

Max Activating Token Index: 855

Text #15

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1071571 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1727268 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6296. Min Act: -0.0000

Data Index: 995554 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1603142 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1957079 (The Pile)

Max Activating Token Index: 195