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

Dataset: The Pile

Neuron 1622 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: 0.3225. Min Range: -0.3225

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1860699 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2221. Min Act: -0.0000

Data Index: 602048 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1899775 (The Pile)

Max Activating Token Index: 751

Text #3

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1230800 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1631564 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1512344 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2163. Min Act: -0.0000

Data Index: 288151 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1645193 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2197. Min Act: -0.0000

Data Index: 686522 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1986. Min Act: -0.0000

Data Index: 659136 (The Pile)

Max Activating Token Index: 237

Text #10

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1667576 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1698955 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1156860 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1394388 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1226898 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1732. Min Act: 0.0000

Data Index: 1115800 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1126717 (The Pile)

Max Activating Token Index: 140

Text #17

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1142101 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1769. Min Act: -0.0000

Data Index: 664457 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1427453 (The Pile)

Max Activating Token Index: 255