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

Dataset: The Pile

Neuron 861 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1382. Min Act: 0.0000

Data Index: 809631 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1071619 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1083055 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1857001 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0595. Min Act: 0.0000

Data Index: 238273 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0551. Min Act: -0.0000

Data Index: 197895 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0541. Min Act: -0.0000

Data Index: 527260 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0541. Min Act: 0.0000

Data Index: 1436513 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0560. Min Act: 0.0000

Data Index: 1176916 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0535. Min Act: -0.0000

Data Index: 178062 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0553. Min Act: 0.0000

Data Index: 1737437 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0531. Min Act: 0.0000

Data Index: 456802 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1362875 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0520. Min Act: 0.0000

Data Index: 138441 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0519. Min Act: 0.0000

Data Index: 818412 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0519. Min Act: 0.0000

Data Index: 1085673 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0518. Min Act: -0.0000

Data Index: 389908 (The Pile)

Max Activating Token Index: 504

Text #17

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0531. Min Act: -0.0000

Data Index: 16991 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1777933 (The Pile)

Max Activating Token Index: 265

Text #19

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0507. Min Act: 0.0000

Data Index: 202346 (The Pile)

Max Activating Token Index: 534