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

Dataset: The Pile

Neuron 2018 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: 5.0553. Min Range: -5.0553

Max Act: 5.0553. Min Act: -0.0000

Data Index: 725920 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 5.0553. Min Range: -5.0553

Max Act: 4.5995. Min Act: -0.0000

Data Index: 1191610 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 5.0553. Min Range: -5.0553

Max Act: 4.9472. Min Act: -0.0000

Data Index: 940657 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 5.0553. Min Range: -5.0553

Max Act: 4.3882. Min Act: -0.0000

Data Index: 1357288 (The Pile)

Max Activating Token Index: 342

Text #4

Max Range: 5.0553. Min Range: -5.0553

Max Act: 4.3677. Min Act: -0.0000

Data Index: 1069623 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 5.0553. Min Range: -5.0553

Max Act: 4.0035. Min Act: -0.0000

Data Index: 1373852 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 5.0553. Min Range: -5.0553

Max Act: 3.8604. Min Act: -0.0000

Data Index: 1221982 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 5.0553. Min Range: -5.0553

Max Act: 3.3452. Min Act: -0.0000

Data Index: 1037216 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 5.0553. Min Range: -5.0553

Max Act: 3.2517. Min Act: -0.0000

Data Index: 1495411 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 5.0553. Min Range: -5.0553

Max Act: 3.4797. Min Act: -0.0000

Data Index: 1769865 (The Pile)

Max Activating Token Index: 662

Text #10

Max Range: 5.0553. Min Range: -5.0553

Max Act: 3.5971. Min Act: -0.0000

Data Index: 1605297 (The Pile)

Max Activating Token Index: 883

Text #11

Max Range: 5.0553. Min Range: -5.0553

Max Act: 2.5899. Min Act: -0.0000

Data Index: 446434 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 5.0553. Min Range: -5.0553

Max Act: 3.1286. Min Act: -0.0000

Data Index: 1461004 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 5.0553. Min Range: -5.0553

Max Act: 2.9976. Min Act: -0.0000

Data Index: 642957 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 5.0553. Min Range: -5.0553

Max Act: 3.2267. Min Act: -0.0000

Data Index: 1214030 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 5.0553. Min Range: -5.0553

Max Act: 3.2091. Min Act: -0.0000

Data Index: 1382381 (The Pile)

Max Activating Token Index: 808

Text #16

Max Range: 5.0553. Min Range: -5.0553

Max Act: 2.9013. Min Act: -0.0000

Data Index: 1587375 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 5.0553. Min Range: -5.0553

Max Act: 2.9377. Min Act: -0.0000

Data Index: 1617520 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 5.0553. Min Range: -5.0553

Max Act: 3.0022. Min Act: -0.0000

Data Index: 1515801 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 5.0553. Min Range: -5.0553

Max Act: 2.8484. Min Act: -0.0000

Data Index: 1656778 (The Pile)

Max Activating Token Index: 100