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

Dataset: The Pile

Neuron 2921 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: 0.6010. Min Range: -0.6010

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1038387 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1294602 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1551722 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1394850 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4876. Min Act: -0.0000

Data Index: 987902 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1849541 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5043. Min Act: -0.0000

Data Index: 605761 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1980219 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4848. Min Act: -0.0000

Data Index: 677688 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4796. Min Act: -0.0000

Data Index: 300769 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4632. Min Act: -0.0000

Data Index: 492537 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4765. Min Act: -0.0000

Data Index: 172364 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4864. Min Act: -0.0000

Data Index: 628831 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4369. Min Act: -0.0000

Data Index: 233392 (The Pile)

Max Activating Token Index: 893

Text #14

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4432. Min Act: -0.0000

Data Index: 976965 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4576. Min Act: -0.0000

Data Index: 979312 (The Pile)

Max Activating Token Index: 682

Text #16

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1500028 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1062052 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4371. Min Act: -0.0000

Data Index: 427626 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1302570 (The Pile)

Max Activating Token Index: 51