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

Dataset: The Pile

Neuron 4163 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.2447. Min Act: -0.0000

Data Index: 512695 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.2186. Min Act: -0.0000

Data Index: 274003 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1785073 (The Pile)

Max Activating Token Index: 651

Text #3

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.9255. Min Act: -0.0000

Data Index: 731396 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.9100. Min Act: -0.0000

Data Index: 317304 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1658486 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1719765 (The Pile)

Max Activating Token Index: 756

Text #7

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.9154. Min Act: -0.0000

Data Index: 296686 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1897982 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8995. Min Act: -0.0000

Data Index: 515401 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1898689 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1812231 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1843825 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1818073 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8645. Min Act: -0.0000

Data Index: 589472 (The Pile)

Max Activating Token Index: 454

Text #15

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1170224 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8269. Min Act: -0.0000

Data Index: 317915 (The Pile)

Max Activating Token Index: 800

Text #17

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8556. Min Act: -0.0000

Data Index: 730115 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1366803 (The Pile)

Max Activating Token Index: 984

Text #19

Max Range: 1.2447. Min Range: -1.2447

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1395547 (The Pile)

Max Activating Token Index: 45