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

Dataset: The Pile

Neuron 1771 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: 1.2325. Min Range: -1.2325

Max Act: 1.1645. Min Act: -0.0000

Data Index: 843303 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.1368. Min Act: -0.0000

Data Index: 1129621 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.2325. Min Act: -0.0000

Data Index: 878891 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0720. Min Act: -0.0000

Data Index: 126858 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1687202 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1169064 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0359. Min Act: -0.0000

Data Index: 219392 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1551989 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1062156 (The Pile)

Max Activating Token Index: 773

Text #9

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1735716 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0742. Min Act: -0.0000

Data Index: 7815 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0058. Min Act: -0.0000

Data Index: 626364 (The Pile)

Max Activating Token Index: 524

Text #12

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1360299 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0324. Min Act: -0.0000

Data Index: 533389 (The Pile)

Max Activating Token Index: 621

Text #14

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9717. Min Act: -0.0000

Data Index: 281400 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1496508 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9614. Min Act: -0.0000

Data Index: 485704 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9789. Min Act: -0.0000

Data Index: 1702967 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1286854 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9432. Min Act: -0.0000

Data Index: 503102 (The Pile)

Max Activating Token Index: 396