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

Dataset: The Pile

Neuron 5112 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.3608. Min Act: -0.0000

Data Index: 950402 (The Pile)

Max Activating Token Index: 468

Text #1

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1499026 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1830498 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.2179. Min Act: -0.0000

Data Index: 680485 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1578951 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1545868 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.0455. Min Act: -0.0000

Data Index: 498292 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.0668. Min Act: -0.0000

Data Index: 245986 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.1012. Min Act: -0.0000

Data Index: 124901 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1174753 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1399774 (The Pile)

Max Activating Token Index: 830

Text #11

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1448071 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1699625 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.9015. Min Act: -0.0000

Data Index: 379423 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.8679. Min Act: -0.0000

Data Index: 200584 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.8793. Min Act: -0.0000

Data Index: 979956 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1302856 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.8284. Min Act: -0.0000

Data Index: 293012 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1680452 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1300791 (The Pile)

Max Activating Token Index: 44