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

Dataset: The Pile

Neuron 3839 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: 0.6283. Min Range: -0.6283

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1061481 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1064807 (The Pile)

Max Activating Token Index: 873

Text #2

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1686861 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.5378. Min Act: -0.0000

Data Index: 530276 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.5135. Min Act: -0.0000

Data Index: 92923 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4900. Min Act: -0.0000

Data Index: 95619 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1823159 (The Pile)

Max Activating Token Index: 368

Text #7

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4992. Min Act: -0.0000

Data Index: 559494 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1180974 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1384552 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.5070. Min Act: -0.0000

Data Index: 755893 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1054107 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1767032 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1241660 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1804621 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4542. Min Act: -0.0000

Data Index: 770445 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1902057 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4458. Min Act: -0.0000

Data Index: 940748 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4032. Min Act: -0.0000

Data Index: 261187 (The Pile)

Max Activating Token Index: 670

Text #19

Max Range: 0.6283. Min Range: -0.6283

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1907064 (The Pile)

Max Activating Token Index: 965