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

Dataset: The Pile

Neuron 180 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: 0.9382. Min Range: -0.9382

Max Act: 0.9129. Min Act: -0.0000

Data Index: 554168 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.9250. Min Act: -0.0000

Data Index: 932075 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8878. Min Act: -0.0000

Data Index: 339404 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1342292 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7976. Min Act: -0.0000

Data Index: 91964 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1032107 (The Pile)

Max Activating Token Index: 70

Text #6

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1897269 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1359241 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1879781 (The Pile)

Max Activating Token Index: 770

Text #9

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6715. Min Act: -0.0000

Data Index: 683351 (The Pile)

Max Activating Token Index: 65

Text #10

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1865266 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1964452 (The Pile)

Max Activating Token Index: 806

Text #12

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1479035 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1358078 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1347218 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.5550. Min Act: -0.0000

Data Index: 189409 (The Pile)

Max Activating Token Index: 366

Text #16

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1746728 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6145. Min Act: -0.0000

Data Index: 245345 (The Pile)

Max Activating Token Index: 623

Text #18

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1473976 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1847825 (The Pile)

Max Activating Token Index: 752