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

Dataset: The Pile

Neuron 3235 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: 5.7791. Min Range: -5.7791

Max Act: 4.9237. Min Act: -0.0000

Data Index: 951600 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 5.7791. Min Range: -5.7791

Max Act: 5.2144. Min Act: -0.0000

Data Index: 1328984 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 5.7791. Min Range: -5.7791

Max Act: 5.1649. Min Act: -0.0000

Data Index: 1881917 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 5.7791. Min Range: -5.7791

Max Act: 5.7791. Min Act: 0.0000

Data Index: 299172 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 5.7791. Min Range: -5.7791

Max Act: 5.1424. Min Act: -0.0000

Data Index: 1691996 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 5.7791. Min Range: -5.7791

Max Act: 5.3455. Min Act: 0.0000

Data Index: 1259213 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 5.7791. Min Range: -5.7791

Max Act: 5.1346. Min Act: -0.0000

Data Index: 152781 (The Pile)

Max Activating Token Index: 756

Text #7

Max Range: 5.7791. Min Range: -5.7791

Max Act: 5.1829. Min Act: 0.0000

Data Index: 922604 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.9501. Min Act: -0.0000

Data Index: 564194 (The Pile)

Max Activating Token Index: 72

Text #9

Max Range: 5.7791. Min Range: -5.7791

Max Act: 5.0085. Min Act: -0.0000

Data Index: 1446957 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.7824. Min Act: -0.0000

Data Index: 1701065 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.6849. Min Act: -0.0000

Data Index: 334032 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.8006. Min Act: -0.0000

Data Index: 116853 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.6798. Min Act: -0.0000

Data Index: 1159244 (The Pile)

Max Activating Token Index: 649

Text #14

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.6206. Min Act: -0.0000

Data Index: 72258 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.6342. Min Act: 0.0000

Data Index: 1914866 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.5728. Min Act: 0.0000

Data Index: 378118 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.1800. Min Act: -0.0000

Data Index: 352967 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.2300. Min Act: -0.0000

Data Index: 1406590 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 5.7791. Min Range: -5.7791

Max Act: 4.2089. Min Act: -0.0000

Data Index: 595862 (The Pile)

Max Activating Token Index: 245