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

Dataset: The Pile

Neuron 3018 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0762. Min Act: -0.0000

Data Index: 315781 (The Pile)

Max Activating Token Index: 149

Text #1

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9558. Min Act: -0.0000

Data Index: 89764 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9533. Min Act: -0.0000

Data Index: 937130 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1162540 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1125195 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1427529 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9285. Min Act: -0.0000

Data Index: 653800 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9322. Min Act: -0.0000

Data Index: 176640 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8938. Min Act: -0.0000

Data Index: 933297 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1993147 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9162. Min Act: -0.0000

Data Index: 404918 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1767624 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9160. Min Act: -0.0000

Data Index: 415519 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9077. Min Act: -0.0000

Data Index: 232143 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8768. Min Act: -0.0000

Data Index: 349456 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9164. Min Act: -0.0000

Data Index: 951897 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9360. Min Act: -0.0001

Data Index: 697715 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.9677. Min Act: -0.0000

Data Index: 140465 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8771. Min Act: -0.0000

Data Index: 537174 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1039579 (The Pile)

Max Activating Token Index: 418