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

Dataset: The Pile

Neuron 1312 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7375. Min Act: -0.0000

Data Index: 54841 (The Pile)

Max Activating Token Index: 409

Text #1

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6462. Min Act: -0.0000

Data Index: 6439 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1715406 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7849. Min Act: -0.0000

Data Index: 684796 (The Pile)

Max Activating Token Index: 833

Text #4

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1302463 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1571248 (The Pile)

Max Activating Token Index: 761

Text #6

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1312433 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7483. Min Act: -0.0000

Data Index: 448217 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6778. Min Act: -0.0000

Data Index: 608138 (The Pile)

Max Activating Token Index: 807

Text #9

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7053. Min Act: -0.0000

Data Index: 487428 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1075609 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6435. Min Act: -0.0000

Data Index: 243444 (The Pile)

Max Activating Token Index: 769

Text #12

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1936143 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.5995. Min Act: -0.0000

Data Index: 726854 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1907448 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7571. Min Act: -0.0000

Data Index: 259442 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7099. Min Act: -0.0000

Data Index: 269344 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1496349 (The Pile)

Max Activating Token Index: 462

Text #18

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1198638 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6424. Min Act: -0.0000

Data Index: 931905 (The Pile)

Max Activating Token Index: 553