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

Dataset: The Pile

Neuron 3192 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: 3.2427. Min Range: -3.2427

Max Act: 2.9884. Min Act: -0.0000

Data Index: 1823580 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 3.2427. Min Range: -3.2427

Max Act: 3.2427. Min Act: -0.0000

Data Index: 1980091 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.9838. Min Act: -0.0000

Data Index: 1138810 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.6698. Min Act: -0.0000

Data Index: 778052 (The Pile)

Max Activating Token Index: 859

Text #4

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.6535. Min Act: -0.0000

Data Index: 1556458 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.6084. Min Act: -0.0000

Data Index: 1399140 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.3802. Min Act: -0.0000

Data Index: 1602756 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.4500. Min Act: -0.0000

Data Index: 1487079 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.5831. Min Act: -0.0000

Data Index: 45657 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.6417. Min Act: -0.0000

Data Index: 976426 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.3842. Min Act: -0.0000

Data Index: 553940 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.5071. Min Act: -0.0000

Data Index: 611918 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.2314. Min Act: -0.0000

Data Index: 472046 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.3512. Min Act: -0.0000

Data Index: 373871 (The Pile)

Max Activating Token Index: 885

Text #14

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.4726. Min Act: -0.0000

Data Index: 1190715 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.4581. Min Act: -0.0000

Data Index: 115892 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.5706. Min Act: -0.0000

Data Index: 666389 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.2659. Min Act: -0.0000

Data Index: 651811 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.3992. Min Act: -0.0000

Data Index: 1838894 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 3.2427. Min Range: -3.2427

Max Act: 2.2826. Min Act: -0.0000

Data Index: 1340141 (The Pile)

Max Activating Token Index: 833