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

Dataset: The Pile

Neuron 21 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2339. Min Act: -0.0000

Data Index: 977566 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1857587 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1548909 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1947060 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2024. Min Act: -0.0000

Data Index: 86425 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1436675 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1964. Min Act: -0.0000

Data Index: 373281 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1097948 (The Pile)

Max Activating Token Index: 410

Text #8

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1937. Min Act: -0.0000

Data Index: 558206 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1762. Min Act: -0.0000

Data Index: 885060 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1441235 (The Pile)

Max Activating Token Index: 787

Text #11

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1670300 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1361102 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1380642 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1784825 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1592749 (The Pile)

Max Activating Token Index: 83

Text #16

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1549718 (The Pile)

Max Activating Token Index: 778

Text #17

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1854. Min Act: -0.0000

Data Index: 242358 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1764. Min Act: -0.0000

Data Index: 121819 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1829. Min Act: -0.0000

Data Index: 814374 (The Pile)

Max Activating Token Index: 727