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

Dataset: The Pile

Neuron 3471 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1844609 (The Pile)

Max Activating Token Index: 204

Text #1

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.9734. Min Act: -0.0000

Data Index: 984641 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1992516 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1732837 (The Pile)

Max Activating Token Index: 549

Text #4

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8093. Min Act: -0.0000

Data Index: 529653 (The Pile)

Max Activating Token Index: 653

Text #5

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8315. Min Act: -0.0000

Data Index: 381677 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.8740. Min Act: -0.0000

Data Index: 825785 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1878713 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1185033 (The Pile)

Max Activating Token Index: 513

Text #9

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7517. Min Act: -0.0000

Data Index: 387832 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1374133 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1210617 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1281926 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7385. Min Act: 0.0000

Data Index: 975406 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1965636 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7074. Min Act: -0.0000

Data Index: 509601 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1719882 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.6287. Min Act: -0.0000

Data Index: 135124 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1995775 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 0.9734. Min Range: -0.9734

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1849124 (The Pile)

Max Activating Token Index: 923