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

Dataset: The Pile

Neuron 3945 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.6540. Min Act: -0.0000

Data Index: 1332412 (The Pile)

Max Activating Token Index: 693

Text #1

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1459478 (The Pile)

Max Activating Token Index: 732

Text #2

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1882684 (The Pile)

Max Activating Token Index: 337

Text #3

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.0938. Min Act: -0.0000

Data Index: 680537 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 1.6540. Min Range: -1.6540

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1577383 (The Pile)

Max Activating Token Index: 239

Text #5

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1420341 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.0232. Min Act: -0.0000

Data Index: 77335 (The Pile)

Max Activating Token Index: 997

Text #7

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.0199. Min Act: -0.0000

Data Index: 830869 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 1.6540. Min Range: -1.6540

Max Act: 0.9784. Min Act: -0.0000

Data Index: 148480 (The Pile)

Max Activating Token Index: 1014

Text #9

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.1222. Min Act: -0.0000

Data Index: 592624 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1890795 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 1.6540. Min Range: -1.6540

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1016140 (The Pile)

Max Activating Token Index: 855

Text #12

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1805529 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1185565 (The Pile)

Max Activating Token Index: 743

Text #14

Max Range: 1.6540. Min Range: -1.6540

Max Act: 0.9438. Min Act: -0.0000

Data Index: 87745 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.0972. Min Act: -0.0000

Data Index: 349514 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 1.6540. Min Range: -1.6540

Max Act: 0.9528. Min Act: -0.0000

Data Index: 1944598 (The Pile)

Max Activating Token Index: 774

Text #17

Max Range: 1.6540. Min Range: -1.6540

Max Act: 0.9117. Min Act: -0.0000

Data Index: 200951 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 1.6540. Min Range: -1.6540

Max Act: 0.8291. Min Act: -0.0000

Data Index: 114 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 1.6540. Min Range: -1.6540

Max Act: 0.7973. Min Act: -0.0000

Data Index: 463783 (The Pile)

Max Activating Token Index: 1018