Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3514 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4995. Min Range: -1.4995

Max Act: 1.4995. Min Act: -0.0000

Data Index: 1740617 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 1.4995. Min Range: -1.4995

Max Act: 1.4164. Min Act: -0.0000

Data Index: 474674 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 1.4995. Min Range: -1.4995

Max Act: 1.2233. Min Act: -0.0000

Data Index: 597001 (The Pile)

Max Activating Token Index: 337

Text #3

Max Range: 1.4995. Min Range: -1.4995

Max Act: 1.1261. Min Act: -0.0000

Data Index: 421518 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.4995. Min Range: -1.4995

Max Act: 1.0895. Min Act: -0.0000

Data Index: 356425 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 1.4995. Min Range: -1.4995

Max Act: 1.1374. Min Act: -0.0000

Data Index: 21285 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 1.4995. Min Range: -1.4995

Max Act: 1.1413. Min Act: -0.0000

Data Index: 83326 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 1.4995. Min Range: -1.4995

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1455659 (The Pile)

Max Activating Token Index: 403

Text #8

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1008664 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 1.4995. Min Range: -1.4995

Max Act: 1.0308. Min Act: -0.0000

Data Index: 52671 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1678688 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.9052. Min Act: -0.0000

Data Index: 103373 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1599905 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.8198. Min Act: -0.0000

Data Index: 605268 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1127470 (The Pile)

Max Activating Token Index: 196

Text #15

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.9074. Min Act: -0.0000

Data Index: 329831 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1467134 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.8771. Min Act: -0.0000

Data Index: 813780 (The Pile)

Max Activating Token Index: 432

Text #18

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1057784 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.4995. Min Range: -1.4995

Max Act: 0.8054. Min Act: -0.0000

Data Index: 662237 (The Pile)

Max Activating Token Index: 96