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

Dataset: The Pile

Neuron 1629 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: 1.6060. Min Range: -1.6060

Max Act: 1.6060. Min Act: -0.0000

Data Index: 1317122 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1491338 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.5203. Min Act: -0.0000

Data Index: 1159052 (The Pile)

Max Activating Token Index: 859

Text #3

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.4528. Min Act: -0.0000

Data Index: 65024 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.3611. Min Act: -0.0000

Data Index: 1247352 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.2641. Min Act: -0.0000

Data Index: 1076563 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1184578 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.2424. Min Act: -0.0000

Data Index: 733891 (The Pile)

Max Activating Token Index: 955

Text #8

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.2693. Min Act: -0.0000

Data Index: 532656 (The Pile)

Max Activating Token Index: 554

Text #9

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.2880. Min Act: -0.0000

Data Index: 1152727 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1259112 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.2329. Min Act: -0.0000

Data Index: 1395728 (The Pile)

Max Activating Token Index: 61

Text #12

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.1574. Min Act: -0.0000

Data Index: 849199 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.1821. Min Act: -0.0000

Data Index: 370272 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1498959 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.1385. Min Act: -0.0000

Data Index: 161511 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.1287. Min Act: -0.0000

Data Index: 615278 (The Pile)

Max Activating Token Index: 237

Text #17

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.1348. Min Act: -0.0000

Data Index: 651792 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1730444 (The Pile)

Max Activating Token Index: 915

Text #19

Max Range: 1.6060. Min Range: -1.6060

Max Act: 1.0736. Min Act: -0.0000

Data Index: 125066 (The Pile)

Max Activating Token Index: 248