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

Dataset: The Pile

Neuron 4843 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: 0.2342. Min Range: -0.2342

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1951798 (The Pile)

Max Activating Token Index: 766

Text #1

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1910. Min Act: -0.0000

Data Index: 360627 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1798. Min Act: -0.0000

Data Index: 965777 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1464. Min Act: -0.0000

Data Index: 859141 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1248704 (The Pile)

Max Activating Token Index: 343

Text #5

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1693971 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1989384 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1280382 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1052494 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1679. Min Act: -0.0000

Data Index: 337837 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1433482 (The Pile)

Max Activating Token Index: 674

Text #11

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1113753 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1466. Min Act: -0.0000

Data Index: 522723 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1463. Min Act: -0.0000

Data Index: 688384 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1753639 (The Pile)

Max Activating Token Index: 710

Text #15

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1488591 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1186. Min Act: -0.0000

Data Index: 808108 (The Pile)

Max Activating Token Index: 637

Text #17

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1354. Min Act: -0.0000

Data Index: 237003 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1762881 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1111258 (The Pile)

Max Activating Token Index: 285