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

Dataset: The Pile

Neuron 2542 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1205313 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1370134 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3746. Min Act: -0.0000

Data Index: 379627 (The Pile)

Max Activating Token Index: 755

Text #3

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1533878 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3954. Min Act: -0.0000

Data Index: 649583 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3819. Min Act: -0.0000

Data Index: 52577 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3672. Min Act: -0.0000

Data Index: 180803 (The Pile)

Max Activating Token Index: 880

Text #7

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3758. Min Act: -0.0000

Data Index: 169551 (The Pile)

Max Activating Token Index: 509

Text #8

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1245746 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3890. Min Act: -0.0000

Data Index: 331238 (The Pile)

Max Activating Token Index: 566

Text #10

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3582. Min Act: -0.0000

Data Index: 532317 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3381. Min Act: -0.0000

Data Index: 156486 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1625145 (The Pile)

Max Activating Token Index: 749

Text #13

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1881874 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3536. Min Act: -0.0000

Data Index: 398853 (The Pile)

Max Activating Token Index: 849

Text #15

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3614. Min Act: -0.0000

Data Index: 360216 (The Pile)

Max Activating Token Index: 750

Text #16

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3513. Min Act: -0.0000

Data Index: 851019 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1795979 (The Pile)

Max Activating Token Index: 800

Text #18

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1741899 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 0.5328. Min Range: -0.5328

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1592788 (The Pile)

Max Activating Token Index: 602