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

Dataset: The Pile

Neuron 3203 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: 0.8104. Min Range: -0.8104

Max Act: 0.8104. Min Act: -0.0000

Data Index: 573641 (The Pile)

Max Activating Token Index: 889

Text #1

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6958. Min Act: -0.0000

Data Index: 705822 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7860. Min Act: -0.0000

Data Index: 771254 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7684. Min Act: -0.0000

Data Index: 718474 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7146. Min Act: -0.0000

Data Index: 47274 (The Pile)

Max Activating Token Index: 620

Text #5

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7465. Min Act: -0.0000

Data Index: 286596 (The Pile)

Max Activating Token Index: 914

Text #6

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7456. Min Act: -0.0000

Data Index: 644991 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1589763 (The Pile)

Max Activating Token Index: 819

Text #8

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1622339 (The Pile)

Max Activating Token Index: 981

Text #9

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7424. Min Act: -0.0000

Data Index: 73633 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1833478 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1551663 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1283510 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1818194 (The Pile)

Max Activating Token Index: 347

Text #14

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6418. Min Act: -0.0000

Data Index: 326386 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1370369 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6995. Min Act: -0.0000

Data Index: 856382 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1099976 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6318. Min Act: -0.0000

Data Index: 685551 (The Pile)

Max Activating Token Index: 669

Text #19

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7204. Min Act: -0.0000

Data Index: 112793 (The Pile)

Max Activating Token Index: 445