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

Dataset: The Pile

Neuron 145 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.9927. Min Act: -0.0000

Data Index: 875823 (The Pile)

Max Activating Token Index: 627

Text #1

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1514961 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.4926. Min Act: -0.0000

Data Index: 545920 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1789151 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1242925 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1490014 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7212. Min Act: -0.0000

Data Index: 792965 (The Pile)

Max Activating Token Index: 298

Text #7

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1491639 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6680. Min Act: -0.0000

Data Index: 935521 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1838119 (The Pile)

Max Activating Token Index: 992

Text #10

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1984494 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6780. Min Act: -0.0000

Data Index: 26248 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1480284 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1174571 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6709. Min Act: -0.0000

Data Index: 245499 (The Pile)

Max Activating Token Index: 331

Text #15

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1231643 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1148601 (The Pile)

Max Activating Token Index: 758

Text #17

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.5804. Min Act: -0.0000

Data Index: 453323 (The Pile)

Max Activating Token Index: 103

Text #18

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1381391 (The Pile)

Max Activating Token Index: 757

Text #19

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1474251 (The Pile)

Max Activating Token Index: 140