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

Dataset: The Pile

Neuron 4814 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: 3.9929. Min Range: -3.9929

Max Act: 3.9929. Min Act: -0.0000

Data Index: 1245702 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.7370. Min Act: -0.0000

Data Index: 1596124 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.6118. Min Act: -0.0000

Data Index: 273803 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.4375. Min Act: -0.0000

Data Index: 826389 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.4018. Min Act: -0.0000

Data Index: 1118882 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.7001. Min Act: -0.0000

Data Index: 944958 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.4239. Min Act: -0.0000

Data Index: 986077 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.4367. Min Act: -0.0000

Data Index: 1778201 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.3789. Min Act: -0.0000

Data Index: 556605 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.0999. Min Act: -0.0000

Data Index: 816963 (The Pile)

Max Activating Token Index: 704

Text #10

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.3078. Min Act: -0.0000

Data Index: 495962 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.4698. Min Act: -0.0000

Data Index: 1451386 (The Pile)

Max Activating Token Index: 802

Text #12

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.1817. Min Act: -0.0000

Data Index: 415153 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.1228. Min Act: -0.0000

Data Index: 612997 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.2835. Min Act: -0.0000

Data Index: 437338 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.2448. Min Act: -0.0000

Data Index: 550311 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 3.9929. Min Range: -3.9929

Max Act: 2.9733. Min Act: -0.0000

Data Index: 714156 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 3.9929. Min Range: -3.9929

Max Act: 2.9370. Min Act: -0.0000

Data Index: 783246 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.0599. Min Act: -0.0000

Data Index: 996735 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 3.9929. Min Range: -3.9929

Max Act: 3.0638. Min Act: -0.0000

Data Index: 714456 (The Pile)

Max Activating Token Index: 252