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

Dataset: The Pile

Neuron 778 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.9952. Min Act: 0.0000

Data Index: 469184 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.9055. Min Act: -0.0000

Data Index: 1195940 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.7629. Min Act: -0.0000

Data Index: 1504896 (The Pile)

Max Activating Token Index: 349

Text #3

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.7178. Min Act: -0.0000

Data Index: 1505047 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.7090. Min Act: -0.0000

Data Index: 1289512 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.6310. Min Act: -0.0000

Data Index: 711559 (The Pile)

Max Activating Token Index: 956

Text #6

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.5653. Min Act: -0.0000

Data Index: 1560397 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.6134. Min Act: -0.0000

Data Index: 1118593 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.5203. Min Act: 0.0000

Data Index: 760377 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4952. Min Act: -0.0000

Data Index: 269595 (The Pile)

Max Activating Token Index: 933

Text #10

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.5240. Min Act: 0.0000

Data Index: 682241 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.5021. Min Act: -0.0000

Data Index: 827441 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1754707 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4902. Min Act: -0.0000

Data Index: 172684 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4971. Min Act: -0.0000

Data Index: 113658 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4749. Min Act: 0.0000

Data Index: 305402 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.5688. Min Act: -0.0000

Data Index: 1218543 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4597. Min Act: -0.0000

Data Index: 1497146 (The Pile)

Max Activating Token Index: 421

Text #18

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4525. Min Act: -0.0000

Data Index: 545351 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.3516. Min Act: -0.0000

Data Index: 732803 (The Pile)

Max Activating Token Index: 795