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

Dataset: The Pile

Neuron 4603 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: 4.2865. Min Range: -4.2865

Max Act: 4.2865. Min Act: -0.0000

Data Index: 6407 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.7521. Min Act: -0.0000

Data Index: 1187839 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.5482. Min Act: -0.0000

Data Index: 806338 (The Pile)

Max Activating Token Index: 837

Text #3

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.7585. Min Act: -0.0000

Data Index: 116251 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.9860. Min Act: -0.0000

Data Index: 1323733 (The Pile)

Max Activating Token Index: 988

Text #5

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.5162. Min Act: -0.0000

Data Index: 1156676 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.5112. Min Act: -0.0000

Data Index: 65690 (The Pile)

Max Activating Token Index: 897

Text #7

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.5087. Min Act: -0.0000

Data Index: 886147 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.5112. Min Act: -0.0000

Data Index: 1747342 (The Pile)

Max Activating Token Index: 1012

Text #9

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.8229. Min Act: -0.0000

Data Index: 559048 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.7571. Min Act: -0.0000

Data Index: 1684825 (The Pile)

Max Activating Token Index: 104

Text #11

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.4762. Min Act: -0.0000

Data Index: 1408441 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.4117. Min Act: -0.0000

Data Index: 210585 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.5493. Min Act: -0.0000

Data Index: 679230 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.6170. Min Act: -0.0000

Data Index: 355064 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.5304. Min Act: -0.0000

Data Index: 171470 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.5285. Min Act: -0.0000

Data Index: 273566 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.6835. Min Act: -0.0000

Data Index: 1617732 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.3523. Min Act: -0.0000

Data Index: 782107 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 4.2865. Min Range: -4.2865

Max Act: 3.5368. Min Act: -0.0000

Data Index: 112698 (The Pile)

Max Activating Token Index: 846