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

Dataset: The Pile

Neuron 1966 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: 4.3031. Min Range: -4.3031

Max Act: 4.3031. Min Act: -0.0000

Data Index: 116228 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 4.3031. Min Range: -4.3031

Max Act: 4.1064. Min Act: -0.0000

Data Index: 1124284 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 4.3031. Min Range: -4.3031

Max Act: 4.0895. Min Act: -0.0000

Data Index: 271063 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.9038. Min Act: -0.0000

Data Index: 670478 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.9696. Min Act: -0.0000

Data Index: 1100661 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 4.3031. Min Range: -4.3031

Max Act: 4.0434. Min Act: -0.0000

Data Index: 365752 (The Pile)

Max Activating Token Index: 684

Text #6

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.8458. Min Act: -0.0000

Data Index: 1293206 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 4.3031. Min Range: -4.3031

Max Act: 4.0363. Min Act: -0.0000

Data Index: 1616865 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.6830. Min Act: -0.0000

Data Index: 1508043 (The Pile)

Max Activating Token Index: 752

Text #9

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.6467. Min Act: -0.0000

Data Index: 1865738 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.8091. Min Act: -0.0000

Data Index: 1247486 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.5935. Min Act: -0.0000

Data Index: 838554 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.7280. Min Act: -0.0000

Data Index: 1964963 (The Pile)

Max Activating Token Index: 72

Text #13

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.8810. Min Act: -0.0000

Data Index: 46075 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.6907. Min Act: -0.0000

Data Index: 873238 (The Pile)

Max Activating Token Index: 82

Text #15

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.8622. Min Act: -0.0000

Data Index: 1333882 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.5473. Min Act: -0.0000

Data Index: 184268 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.8087. Min Act: -0.0000

Data Index: 1262630 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.4514. Min Act: -0.0000

Data Index: 358576 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 4.3031. Min Range: -4.3031

Max Act: 3.7371. Min Act: -0.0000

Data Index: 467007 (The Pile)

Max Activating Token Index: 132