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

Dataset: The Pile

Neuron 184 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.1991. Min Act: 0.0001

Data Index: 293599 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8809. Min Act: -0.0000

Data Index: 399486 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9821. Min Act: -0.0000

Data Index: 721734 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 1.1991. Min Range: -1.1991

Max Act: 1.0816. Min Act: -0.0000

Data Index: 623111 (The Pile)

Max Activating Token Index: 989

Text #4

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1924303 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9930. Min Act: 0.0000

Data Index: 1435761 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1266072 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9186. Min Act: 0.0000

Data Index: 1411871 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.7781. Min Act: 0.0000

Data Index: 1664815 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.9559. Min Act: 0.0001

Data Index: 64727 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8365. Min Act: -0.0000

Data Index: 894804 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1925641 (The Pile)

Max Activating Token Index: 330

Text #12

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8642. Min Act: -0.0000

Data Index: 514155 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8632. Min Act: -0.0000

Data Index: 684463 (The Pile)

Max Activating Token Index: 856

Text #14

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8353. Min Act: -0.0000

Data Index: 990678 (The Pile)

Max Activating Token Index: 662

Text #15

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1710499 (The Pile)

Max Activating Token Index: 624

Text #16

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1857484 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1122302 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1451706 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 1.1991. Min Range: -1.1991

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1792056 (The Pile)

Max Activating Token Index: 525