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

Dataset: The Pile

Neuron 3220 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0965. Min Range: -3.0965

Max Act: 3.0965. Min Act: -0.0000

Data Index: 1675645 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 3.0965. Min Range: -3.0965

Max Act: 2.7724. Min Act: -0.0000

Data Index: 931748 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.8421. Min Act: -0.0000

Data Index: 353060 (The Pile)

Max Activating Token Index: 581

Text #3

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.9268. Min Act: -0.0000

Data Index: 103926 (The Pile)

Max Activating Token Index: 695

Text #4

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.9460. Min Act: -0.0000

Data Index: 1506781 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.8377. Min Act: -0.0000

Data Index: 1415795 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.8464. Min Act: -0.0000

Data Index: 1305146 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.8170. Min Act: -0.0000

Data Index: 1468652 (The Pile)

Max Activating Token Index: 546

Text #8

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.6358. Min Act: -0.0000

Data Index: 1467883 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.7992. Min Act: -0.0000

Data Index: 1131836 (The Pile)

Max Activating Token Index: 890

Text #10

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.6352. Min Act: -0.0000

Data Index: 1907709 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.6140. Min Act: -0.0000

Data Index: 867324 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.6106. Min Act: -0.0000

Data Index: 1563891 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.5976. Min Act: -0.0000

Data Index: 1674167 (The Pile)

Max Activating Token Index: 816

Text #14

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.7099. Min Act: -0.0000

Data Index: 1450347 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1151766 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.6743. Min Act: -0.0000

Data Index: 1758345 (The Pile)

Max Activating Token Index: 310

Text #17

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.7857. Min Act: -0.0000

Data Index: 1374560 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.6774. Min Act: -0.0000

Data Index: 1733903 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 3.0965. Min Range: -3.0965

Max Act: 1.6363. Min Act: -0.0000

Data Index: 167279 (The Pile)

Max Activating Token Index: 961