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

Dataset: The Pile

Neuron 549 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: 5.0067. Min Range: -5.0067

Max Act: 5.0067. Min Act: -0.0000

Data Index: 785916 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 5.0067. Min Range: -5.0067

Max Act: 4.4877. Min Act: -0.0000

Data Index: 327730 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 5.0067. Min Range: -5.0067

Max Act: 4.2209. Min Act: -0.0000

Data Index: 1693353 (The Pile)

Max Activating Token Index: 924

Text #3

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.9178. Min Act: -0.0000

Data Index: 1581024 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 5.0067. Min Range: -5.0067

Max Act: 4.1898. Min Act: -0.0000

Data Index: 922617 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 5.0067. Min Range: -5.0067

Max Act: 4.1463. Min Act: -0.0000

Data Index: 711536 (The Pile)

Max Activating Token Index: 824

Text #6

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.7747. Min Act: -0.0000

Data Index: 958795 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 5.0067. Min Range: -5.0067

Max Act: 4.0330. Min Act: -0.0000

Data Index: 485321 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.6824. Min Act: -0.0000

Data Index: 1437114 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.8200. Min Act: -0.0000

Data Index: 888043 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.8290. Min Act: -0.0000

Data Index: 1663597 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.7880. Min Act: -0.0000

Data Index: 1515449 (The Pile)

Max Activating Token Index: 1006

Text #12

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.7214. Min Act: -0.0000

Data Index: 1158344 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.4065. Min Act: -0.0000

Data Index: 306663 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.7004. Min Act: -0.0000

Data Index: 619273 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.6862. Min Act: -0.0000

Data Index: 660631 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.5057. Min Act: -0.0000

Data Index: 1796092 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.6564. Min Act: -0.0000

Data Index: 926946 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.6286. Min Act: -0.0000

Data Index: 857483 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 5.0067. Min Range: -5.0067

Max Act: 3.7716. Min Act: -0.0000

Data Index: 695059 (The Pile)

Max Activating Token Index: 719