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

Dataset: The Pile

Neuron 4294 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: 3.9124. Min Range: -3.9124

Max Act: 3.9124. Min Act: -0.0000

Data Index: 275532 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.5496. Min Act: -0.0000

Data Index: 1755294 (The Pile)

Max Activating Token Index: 625

Text #2

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.4189. Min Act: -0.0000

Data Index: 868987 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.2570. Min Act: -0.0000

Data Index: 931237 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.0805. Min Act: -0.0000

Data Index: 522598 (The Pile)

Max Activating Token Index: 388

Text #5

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.0586. Min Act: -0.0000

Data Index: 740114 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.0231. Min Act: -0.0000

Data Index: 1251577 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.8884. Min Act: -0.0000

Data Index: 484396 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.9996. Min Act: -0.0000

Data Index: 35106 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.6794. Min Act: -0.0000

Data Index: 1156612 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.7933. Min Act: -0.0000

Data Index: 1850350 (The Pile)

Max Activating Token Index: 82

Text #11

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.0565. Min Act: -0.0000

Data Index: 1413165 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.7683. Min Act: -0.0000

Data Index: 644591 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.7779. Min Act: -0.0000

Data Index: 1507290 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.7536. Min Act: -0.0000

Data Index: 1807093 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.8546. Min Act: -0.0000

Data Index: 746031 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.6909. Min Act: -0.0000

Data Index: 1347301 (The Pile)

Max Activating Token Index: 810

Text #17

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.0952. Min Act: -0.0000

Data Index: 1114019 (The Pile)

Max Activating Token Index: 122

Text #18

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.9546. Min Act: -0.0000

Data Index: 1785686 (The Pile)

Max Activating Token Index: 583

Text #19

Max Range: 3.9124. Min Range: -3.9124

Max Act: 2.9525. Min Act: -0.0000

Data Index: 106201 (The Pile)

Max Activating Token Index: 316