Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3797 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.9631. Min Act: -0.0000

Data Index: 1885306 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.9514. Min Act: -0.0000

Data Index: 1255150 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1300522 (The Pile)

Max Activating Token Index: 535

Text #3

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.2659. Min Act: -0.0000

Data Index: 402451 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1656412 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1387623 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.0301. Min Act: -0.0000

Data Index: 255611 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1805131 (The Pile)

Max Activating Token Index: 345

Text #8

Max Range: 1.9631. Min Range: -1.9631

Max Act: 0.9782. Min Act: -0.0000

Data Index: 1241686 (The Pile)

Max Activating Token Index: 493

Text #9

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.1479. Min Act: -0.0000

Data Index: 1406872 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.1351. Min Act: -0.0000

Data Index: 453151 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1125093 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1714627 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 1.9631. Min Range: -1.9631

Max Act: 0.9450. Min Act: -0.0000

Data Index: 751775 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.0928. Min Act: -0.0000

Data Index: 791175 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.1256. Min Act: -0.0000

Data Index: 179008 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.0484. Min Act: -0.0000

Data Index: 728922 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 1.9631. Min Range: -1.9631

Max Act: 0.9929. Min Act: -0.0000

Data Index: 278767 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.1211. Min Act: -0.0000

Data Index: 935991 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 1.9631. Min Range: -1.9631

Max Act: 1.0839. Min Act: -0.0000

Data Index: 227154 (The Pile)

Max Activating Token Index: 261