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

Dataset: The Pile

Neuron 4041 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: 2.1949. Min Range: -2.1949

Max Act: 2.1949. Min Act: -0.0000

Data Index: 677980 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 2.1949. Min Range: -2.1949

Max Act: 2.1118. Min Act: -0.0000

Data Index: 1434121 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.9809. Min Act: -0.0000

Data Index: 1059297 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 2.1949. Min Range: -2.1949

Max Act: 2.0882. Min Act: -0.0000

Data Index: 1139632 (The Pile)

Max Activating Token Index: 924

Text #4

Max Range: 2.1949. Min Range: -2.1949

Max Act: 2.0885. Min Act: -0.0000

Data Index: 1898495 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.8973. Min Act: -0.0000

Data Index: 596223 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 2.1949. Min Range: -2.1949

Max Act: 2.0031. Min Act: -0.0000

Data Index: 1168834 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 2.1949. Min Range: -2.1949

Max Act: 2.0049. Min Act: -0.0000

Data Index: 1876124 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.8392. Min Act: -0.0000

Data Index: 1496579 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.9270. Min Act: -0.0000

Data Index: 1048351 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.8348. Min Act: -0.0000

Data Index: 1592413 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 2.1949. Min Range: -2.1949

Max Act: 2.0240. Min Act: -0.0000

Data Index: 1909686 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.9315. Min Act: -0.0000

Data Index: 1933988 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.9123. Min Act: -0.0000

Data Index: 271263 (The Pile)

Max Activating Token Index: 118

Text #14

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.8685. Min Act: -0.0000

Data Index: 343381 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.8315. Min Act: -0.0000

Data Index: 167617 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.8527. Min Act: -0.0000

Data Index: 1836049 (The Pile)

Max Activating Token Index: 637

Text #17

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.9392. Min Act: -0.0000

Data Index: 818657 (The Pile)

Max Activating Token Index: 83

Text #18

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.8359. Min Act: -0.0000

Data Index: 1229323 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.8183. Min Act: -0.0000

Data Index: 610085 (The Pile)

Max Activating Token Index: 786