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

Dataset: The Pile

Neuron 583 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: 1.1578. Min Range: -1.1578

Max Act: 1.1578. Min Act: -0.0000

Data Index: 738967 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.1336. Min Act: -0.0000

Data Index: 1691226 (The Pile)

Max Activating Token Index: 798

Text #2

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0452. Min Act: -0.0000

Data Index: 33653 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0084. Min Act: -0.0000

Data Index: 969875 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1249458 (The Pile)

Max Activating Token Index: 296

Text #5

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1350459 (The Pile)

Max Activating Token Index: 925

Text #6

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1702488 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9496. Min Act: -0.0000

Data Index: 699010 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9893. Min Act: -0.0000

Data Index: 742068 (The Pile)

Max Activating Token Index: 656

Text #9

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1643796 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1173705 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1656486 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8755. Min Act: -0.0000

Data Index: 992184 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9879. Min Act: -0.0000

Data Index: 617453 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1695069 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8413. Min Act: -0.0000

Data Index: 256070 (The Pile)

Max Activating Token Index: 426

Text #16

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8622. Min Act: -0.0000

Data Index: 266570 (The Pile)

Max Activating Token Index: 743

Text #17

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1491927 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8737. Min Act: -0.0000

Data Index: 277403 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9355. Min Act: -0.0000

Data Index: 637945 (The Pile)

Max Activating Token Index: 644