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

Dataset: The Pile

Neuron 1797 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1507635 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1933172 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.4646. Min Act: -0.0000

Data Index: 1996519 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2795. Min Act: -0.0000

Data Index: 670624 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.4648. Min Act: -0.0000

Data Index: 1886408 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2012. Min Act: -0.0000

Data Index: 1430641 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2012. Min Act: -0.0000

Data Index: 131166 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.4525. Min Act: -0.0000

Data Index: 324302 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1147311 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1166559 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1524667 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.1925. Min Act: -0.0000

Data Index: 568734 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2921. Min Act: -0.0000

Data Index: 661423 (The Pile)

Max Activating Token Index: 353

Text #13

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.1926. Min Act: -0.0000

Data Index: 1726205 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.1965. Min Act: -0.0000

Data Index: 615238 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1734251 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2098. Min Act: -0.0000

Data Index: 128726 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2291. Min Act: -0.0000

Data Index: 1581878 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.2827. Min Act: -0.0000

Data Index: 1297939 (The Pile)

Max Activating Token Index: 670

Text #19

Max Range: 1.5127. Min Range: -1.5127

Max Act: 1.1922. Min Act: -0.0000

Data Index: 1289899 (The Pile)

Max Activating Token Index: 246