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

Dataset: The Pile

Neuron 3246 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: 0.6647. Min Range: -0.6647

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1105158 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.6087. Min Act: -0.0000

Data Index: 145208 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1060067 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1294149 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1378386 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5734. Min Act: -0.0000

Data Index: 246942 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1376865 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1227097 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1728446 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1017085 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1534915 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4677. Min Act: -0.0000

Data Index: 133559 (The Pile)

Max Activating Token Index: 955

Text #12

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1348919 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4577. Min Act: -0.0000

Data Index: 527578 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1771162 (The Pile)

Max Activating Token Index: 811

Text #15

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1386899 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1301545 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4687. Min Act: -0.0000

Data Index: 44506 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1260907 (The Pile)

Max Activating Token Index: 171

Text #19

Max Range: 0.6647. Min Range: -0.6647

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1191163 (The Pile)

Max Activating Token Index: 125