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

Dataset: The Pile

Neuron 3502 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1437244 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8395. Min Act: -0.0000

Data Index: 500450 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1302420 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1233936 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1957534 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8153. Min Act: -0.0000

Data Index: 816945 (The Pile)

Max Activating Token Index: 716

Text #6

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1733143 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1996271 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8517. Min Act: -0.0000

Data Index: 605179 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1650714 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8044. Min Act: -0.0000

Data Index: 362822 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7436. Min Act: -0.0000

Data Index: 244041 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6935. Min Act: -0.0000

Data Index: 655625 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1607635 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7310. Min Act: -0.0000

Data Index: 625898 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1068089 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7180. Min Act: -0.0000

Data Index: 755283 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7714. Min Act: -0.0000

Data Index: 819167 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1258383 (The Pile)

Max Activating Token Index: 164

Text #19

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1265542 (The Pile)

Max Activating Token Index: 106