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

Dataset: The Pile

Neuron 1964 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: 0.8854. Min Range: -0.8854

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1044807 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1103390 (The Pile)

Max Activating Token Index: 348

Text #2

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6826. Min Act: -0.0000

Data Index: 786328 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1630496 (The Pile)

Max Activating Token Index: 384

Text #4

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6560. Min Act: -0.0000

Data Index: 543594 (The Pile)

Max Activating Token Index: 38

Text #5

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6405. Min Act: 0.0000

Data Index: 123045 (The Pile)

Max Activating Token Index: 348

Text #6

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1892577 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1419241 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5464. Min Act: -0.0000

Data Index: 480324 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1010010 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5347. Min Act: -0.0000

Data Index: 860438 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5484. Min Act: -0.0000

Data Index: 905898 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5360. Min Act: -0.0000

Data Index: 179642 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1736758 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1013227 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1808513 (The Pile)

Max Activating Token Index: 372

Text #16

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5332. Min Act: -0.0000

Data Index: 761183 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5190. Min Act: -0.0000

Data Index: 87073 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1221514 (The Pile)

Max Activating Token Index: 652

Text #19

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1241786 (The Pile)

Max Activating Token Index: 824