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

Dataset: The Pile

Neuron 2839 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1877932 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4324. Min Act: -0.0000

Data Index: 225638 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4370. Min Act: -0.0000

Data Index: 861670 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1688731 (The Pile)

Max Activating Token Index: 521

Text #4

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4120. Min Act: -0.0000

Data Index: 874186 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4449. Min Act: -0.0000

Data Index: 509211 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1291258 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1267719 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3945. Min Act: -0.0000

Data Index: 713825 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3656. Min Act: -0.0000

Data Index: 474153 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1905204 (The Pile)

Max Activating Token Index: 801

Text #11

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1533471 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3642. Min Act: -0.0000

Data Index: 112798 (The Pile)

Max Activating Token Index: 1013

Text #13

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3314. Min Act: -0.0000

Data Index: 875545 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1540546 (The Pile)

Max Activating Token Index: 785

Text #15

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1342293 (The Pile)

Max Activating Token Index: 421

Text #16

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1122376 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3272. Min Act: -0.0000

Data Index: 115400 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3397. Min Act: -0.0000

Data Index: 483188 (The Pile)

Max Activating Token Index: 688

Text #19

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3393. Min Act: -0.0000

Data Index: 117349 (The Pile)

Max Activating Token Index: 625