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

Dataset: The Pile

Neuron 548 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: 1.3617. Min Range: -1.3617

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1740806 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2999. Min Act: -0.0000

Data Index: 605420 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1072102 (The Pile)

Max Activating Token Index: 536

Text #3

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.9333. Min Act: -0.0000

Data Index: 404334 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.8864. Min Act: -0.0000

Data Index: 247564 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1940740 (The Pile)

Max Activating Token Index: 881

Text #6

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7348. Min Act: -0.0000

Data Index: 572157 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1651255 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1910474 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1997828 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7088. Min Act: 0.0001

Data Index: 1386318 (The Pile)

Max Activating Token Index: 41

Text #11

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7105. Min Act: -0.0000

Data Index: 110104 (The Pile)

Max Activating Token Index: 359

Text #12

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1102201 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7651. Min Act: -0.0000

Data Index: 389164 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1493354 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1594794 (The Pile)

Max Activating Token Index: 792

Text #16

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1176307 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1323214 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.6061. Min Act: -0.0000

Data Index: 621456 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1422637 (The Pile)

Max Activating Token Index: 979