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

Dataset: The Pile

Neuron 3052 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: 1.5105. Min Range: -1.5105

Max Act: 1.5105. Min Act: -0.0000

Data Index: 1122018 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.3995. Min Act: -0.0000

Data Index: 1341384 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.1810. Min Act: -0.0000

Data Index: 642176 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1003828 (The Pile)

Max Activating Token Index: 381

Text #4

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.4047. Min Act: -0.0000

Data Index: 63621 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.1592. Min Act: -0.0000

Data Index: 1123231 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.1050. Min Act: -0.0000

Data Index: 831173 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.1647. Min Act: -0.0000

Data Index: 849990 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.0985. Min Act: -0.0000

Data Index: 288935 (The Pile)

Max Activating Token Index: 560

Text #9

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1046072 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.2050. Min Act: -0.0000

Data Index: 1204797 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.1308. Min Act: -0.0000

Data Index: 1785655 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.2020. Min Act: -0.0000

Data Index: 1401771 (The Pile)

Max Activating Token Index: 270

Text #13

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.0424. Min Act: -0.0000

Data Index: 1612177 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.0116. Min Act: -0.0000

Data Index: 549360 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1209034 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1089428 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1717135 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 1.5105. Min Range: -1.5105

Max Act: 1.1424. Min Act: -0.0000

Data Index: 518668 (The Pile)

Max Activating Token Index: 48

Text #19

Max Range: 1.5105. Min Range: -1.5105

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1023376 (The Pile)

Max Activating Token Index: 678