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

Dataset: The Pile

Neuron 4203 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: 1.0653. Min Range: -1.0653

Max Act: 1.0653. Min Act: -0.0000

Data Index: 268283 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9780. Min Act: -0.0000

Data Index: 230905 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9347. Min Act: -0.0000

Data Index: 189980 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1921241 (The Pile)

Max Activating Token Index: 195

Text #4

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1991622 (The Pile)

Max Activating Token Index: 565

Text #5

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9256. Min Act: -0.0000

Data Index: 963842 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9054. Min Act: -0.0000

Data Index: 546315 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1959224 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1771396 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.8116. Min Act: -0.0000

Data Index: 189468 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.7130. Min Act: -0.0000

Data Index: 871958 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1020059 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.8189. Min Act: -0.0000

Data Index: 940229 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1904752 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1018772 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1008409 (The Pile)

Max Activating Token Index: 349

Text #16

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1100808 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.6981. Min Act: -0.0000

Data Index: 364481 (The Pile)

Max Activating Token Index: 694

Text #18

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.6955. Min Act: -0.0000

Data Index: 508308 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1529812 (The Pile)

Max Activating Token Index: 299