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

Dataset: The Pile

Neuron 196 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: 0.3852. Min Range: -0.3852

Max Act: 0.3556. Min Act: -0.0000

Data Index: 97680 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3852. Min Act: -0.0000

Data Index: 263434 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1372074 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3425. Min Act: -0.0000

Data Index: 124919 (The Pile)

Max Activating Token Index: 177

Text #4

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3394. Min Act: -0.0000

Data Index: 334686 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1873674 (The Pile)

Max Activating Token Index: 761

Text #6

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1163605 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3014. Min Act: -0.0000

Data Index: 598645 (The Pile)

Max Activating Token Index: 968

Text #8

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1266073 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1033103 (The Pile)

Max Activating Token Index: 71

Text #10

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1446512 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2879. Min Act: -0.0000

Data Index: 718249 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1569043 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2834. Min Act: -0.0000

Data Index: 349832 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2823. Min Act: -0.0000

Data Index: 968593 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2479. Min Act: -0.0000

Data Index: 826543 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2708. Min Act: -0.0000

Data Index: 625115 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1636792 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1445664 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2774. Min Act: -0.0000

Data Index: 369647 (The Pile)

Max Activating Token Index: 1019