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

Dataset: The Pile

Neuron 4199 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.6419. Min Act: -0.0000

Data Index: 798125 (The Pile)

Max Activating Token Index: 509

Text #1

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4756. Min Act: -0.0000

Data Index: 855494 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1808687 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.4968. Min Act: -0.0000

Data Index: 1630813 (The Pile)

Max Activating Token Index: 720

Text #4

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3807. Min Act: -0.0000

Data Index: 1723710 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 1.6419. Min Range: -1.6419

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1522946 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.2502. Min Act: -0.0000

Data Index: 1746941 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.1823. Min Act: -0.0000

Data Index: 284617 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.3031. Min Act: -0.0000

Data Index: 983644 (The Pile)

Max Activating Token Index: 847

Text #9

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.1383. Min Act: -0.0000

Data Index: 351022 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 1.6419. Min Range: -1.6419

Max Act: 0.9439. Min Act: -0.0000

Data Index: 303658 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.0276. Min Act: -0.0000

Data Index: 1460876 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.0142. Min Act: -0.0000

Data Index: 777940 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1387842 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.2748. Min Act: -0.0000

Data Index: 405497 (The Pile)

Max Activating Token Index: 892

Text #15

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.2142. Min Act: -0.0000

Data Index: 212956 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 1.6419. Min Range: -1.6419

Max Act: 0.9206. Min Act: -0.0000

Data Index: 740819 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 1.6419. Min Range: -1.6419

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1507105 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.6419. Min Range: -1.6419

Max Act: 0.9797. Min Act: -0.0000

Data Index: 55502 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 1.6419. Min Range: -1.6419

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1194298 (The Pile)

Max Activating Token Index: 313