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

Dataset: The Pile

Neuron 529 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: 1.8012. Min Range: -1.8012

Max Act: 1.7009. Min Act: -0.0000

Data Index: 249966 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.8012. Min Act: -0.0000

Data Index: 151481 (The Pile)

Max Activating Token Index: 34

Text #2

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.5486. Min Act: -0.0000

Data Index: 860423 (The Pile)

Max Activating Token Index: 28

Text #3

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.5457. Min Act: -0.0000

Data Index: 1399930 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.5482. Min Act: -0.0000

Data Index: 1214074 (The Pile)

Max Activating Token Index: 409

Text #5

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.5104. Min Act: -0.0000

Data Index: 438922 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.5084. Min Act: -0.0000

Data Index: 62154 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.4339. Min Act: -0.0000

Data Index: 438562 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3219. Min Act: -0.0000

Data Index: 373323 (The Pile)

Max Activating Token Index: 644

Text #9

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.6780. Min Act: -0.0000

Data Index: 1764487 (The Pile)

Max Activating Token Index: 184

Text #10

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.4414. Min Act: -0.0000

Data Index: 540167 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3173. Min Act: -0.0000

Data Index: 932559 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3682. Min Act: -0.0000

Data Index: 305005 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1767901 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1556682 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3095. Min Act: -0.0000

Data Index: 710965 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1387722 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3787. Min Act: -0.0000

Data Index: 1520203 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1953638 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.2538. Min Act: -0.0000

Data Index: 1043251 (The Pile)

Max Activating Token Index: 725