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

Dataset: The Pile

Neuron 2683 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.6715. Min Act: -0.0000

Data Index: 1559175 (The Pile)

Max Activating Token Index: 701

Text #1

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.8527. Min Act: -0.0000

Data Index: 576966 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.8353. Min Act: -0.0000

Data Index: 271200 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.6270. Min Act: -0.0000

Data Index: 331591 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.6987. Min Act: -0.0000

Data Index: 1588954 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.6315. Min Act: -0.0000

Data Index: 1953381 (The Pile)

Max Activating Token Index: 899

Text #6

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.6375. Min Act: -0.0000

Data Index: 487817 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.4571. Min Act: -0.0000

Data Index: 623817 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.6604. Min Act: -0.0000

Data Index: 715930 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.5997. Min Act: -0.0000

Data Index: 1836817 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.4189. Min Act: -0.0000

Data Index: 326891 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.4971. Min Act: -0.0000

Data Index: 1973277 (The Pile)

Max Activating Token Index: 265

Text #12

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.4977. Min Act: -0.0000

Data Index: 87855 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.3958. Min Act: -0.0000

Data Index: 906316 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.4431. Min Act: -0.0000

Data Index: 865816 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1984323 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.4615. Min Act: -0.0000

Data Index: 1751241 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.4175. Min Act: -0.0000

Data Index: 1339917 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.4451. Min Act: -0.0000

Data Index: 206348 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 1.8527. Min Range: -1.8527

Max Act: 1.3624. Min Act: -0.0000

Data Index: 817751 (The Pile)

Max Activating Token Index: 635