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

Dataset: The Pile

Neuron 4636 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.5068. Min Act: -0.0000

Data Index: 206518 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4580. Min Act: -0.0000

Data Index: 980769 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1372834 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3382. Min Act: -0.0000

Data Index: 972702 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1580384 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3080. Min Act: -0.0000

Data Index: 11182 (The Pile)

Max Activating Token Index: 730

Text #6

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2663. Min Act: -0.0000

Data Index: 684943 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1563698 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1512833 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1565834 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1261480 (The Pile)

Max Activating Token Index: 215

Text #11

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1659549 (The Pile)

Max Activating Token Index: 1012

Text #12

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1991545 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2493. Min Act: -0.0000

Data Index: 100015 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2800. Min Act: -0.0000

Data Index: 4158 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2597. Min Act: -0.0000

Data Index: 206079 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1695386 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1225307 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1439132 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.2820. Min Act: -0.0000

Data Index: 238512 (The Pile)

Max Activating Token Index: 868