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

Dataset: The Pile

Neuron 2597 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: 0.4814. Min Range: -0.4814

Max Act: 0.4814. Min Act: -0.0000

Data Index: 648015 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4032. Min Act: -0.0000

Data Index: 581092 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1685894 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1729662 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3551. Min Act: -0.0000

Data Index: 690722 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3681. Min Act: -0.0000

Data Index: 971173 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3696. Min Act: -0.0000

Data Index: 826776 (The Pile)

Max Activating Token Index: 725

Text #7

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3525. Min Act: -0.0000

Data Index: 824774 (The Pile)

Max Activating Token Index: 345

Text #8

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3497. Min Act: -0.0000

Data Index: 862390 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3617. Min Act: -0.0000

Data Index: 441114 (The Pile)

Max Activating Token Index: 226

Text #10

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3379. Min Act: -0.0000

Data Index: 61863 (The Pile)

Max Activating Token Index: 306

Text #11

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1604743 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1128753 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3168. Min Act: -0.0000

Data Index: 580199 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3139. Min Act: -0.0000

Data Index: 488119 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3128. Min Act: -0.0000

Data Index: 33366 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3123. Min Act: -0.0000

Data Index: 137932 (The Pile)

Max Activating Token Index: 555

Text #17

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1738589 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3036. Min Act: -0.0000

Data Index: 199153 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1986505 (The Pile)

Max Activating Token Index: 254