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

Dataset: The Pile

Neuron 2792 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1782493 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5879. Min Act: -0.0000

Data Index: 276484 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1081808 (The Pile)

Max Activating Token Index: 220

Text #3

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5080. Min Act: -0.0000

Data Index: 343872 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1954979 (The Pile)

Max Activating Token Index: 282

Text #5

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1788746 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4687. Min Act: -0.0000

Data Index: 564614 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1847295 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4070. Min Act: -0.0000

Data Index: 452500 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4316. Min Act: -0.0000

Data Index: 85833 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4434. Min Act: -0.0000

Data Index: 514489 (The Pile)

Max Activating Token Index: 496

Text #11

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4139. Min Act: -0.0000

Data Index: 231980 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1739525 (The Pile)

Max Activating Token Index: 984

Text #13

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4080. Min Act: -0.0000

Data Index: 492465 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4000. Min Act: -0.0000

Data Index: 954368 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4071. Min Act: -0.0000

Data Index: 554625 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3889. Min Act: -0.0000

Data Index: 384779 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3674. Min Act: -0.0000

Data Index: 707187 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1526075 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3610. Min Act: -0.0000

Data Index: 695869 (The Pile)

Max Activating Token Index: 587