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

Dataset: The Pile

Neuron 363 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1716266 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5586. Min Act: -0.0000

Data Index: 492459 (The Pile)

Max Activating Token Index: 803

Text #2

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1793103 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1441811 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5707. Min Act: -0.0000

Data Index: 98307 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5485. Min Act: -0.0000

Data Index: 452940 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5058. Min Act: -0.0000

Data Index: 559705 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5955. Min Act: -0.0000

Data Index: 897339 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1865690 (The Pile)

Max Activating Token Index: 752

Text #9

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5021. Min Act: -0.0000

Data Index: 114295 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1746761 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.6035. Min Act: -0.0000

Data Index: 759651 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1597690 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5095. Min Act: -0.0000

Data Index: 775187 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1486783 (The Pile)

Max Activating Token Index: 954

Text #15

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4944. Min Act: -0.0000

Data Index: 438652 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5230. Min Act: -0.0000

Data Index: 824565 (The Pile)

Max Activating Token Index: 477

Text #17

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5322. Min Act: -0.0000

Data Index: 503497 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5051. Min Act: -0.0000

Data Index: 707969 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4804. Min Act: -0.0000

Data Index: 802565 (The Pile)

Max Activating Token Index: 161