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

Dataset: The Pile

Neuron 3473 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.8814. Min Act: -0.0000

Data Index: 242450 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.7144. Min Act: -0.0000

Data Index: 603913 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.6762. Min Act: -0.0000

Data Index: 805025 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.5098. Min Act: -0.0000

Data Index: 522051 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.3398. Min Act: -0.0000

Data Index: 936301 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1442553 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.3965. Min Act: -0.0000

Data Index: 1235792 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.5550. Min Act: -0.0000

Data Index: 1738570 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1059879 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.3794. Min Act: -0.0000

Data Index: 416250 (The Pile)

Max Activating Token Index: 653

Text #10

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.2972. Min Act: -0.0000

Data Index: 609295 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1038692 (The Pile)

Max Activating Token Index: 617

Text #12

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.2694. Min Act: -0.0000

Data Index: 305155 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.2541. Min Act: -0.0000

Data Index: 119891 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.3301. Min Act: -0.0000

Data Index: 793423 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.1296. Min Act: -0.0000

Data Index: 377039 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1449696 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.1786. Min Act: -0.0000

Data Index: 314207 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.2236. Min Act: -0.0000

Data Index: 1165850 (The Pile)

Max Activating Token Index: 267

Text #19

Max Range: 1.8814. Min Range: -1.8814

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1700744 (The Pile)

Max Activating Token Index: 555