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

Dataset: The Pile

Neuron 3313 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2612. Min Range: -1.2612

Max Act: 1.2612. Min Act: -0.0000

Data Index: 1480885 (The Pile)

Max Activating Token Index: 217

Text #1

Max Range: 1.2612. Min Range: -1.2612

Max Act: 1.0660. Min Act: -0.0000

Data Index: 665570 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1885036 (The Pile)

Max Activating Token Index: 234

Text #3

Max Range: 1.2612. Min Range: -1.2612

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1123254 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8992. Min Act: 0.0000

Data Index: 1000547 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1461961 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8433. Min Act: -0.0000

Data Index: 650258 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1906169 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.9346. Min Act: -0.0000

Data Index: 825173 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8036. Min Act: -0.0000

Data Index: 826345 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1368493 (The Pile)

Max Activating Token Index: 868

Text #11

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.6997. Min Act: -0.0000

Data Index: 519570 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1274643 (The Pile)

Max Activating Token Index: 267

Text #13

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.7225. Min Act: -0.0000

Data Index: 1812718 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1773889 (The Pile)

Max Activating Token Index: 502

Text #15

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.7262. Min Act: -0.0000

Data Index: 419209 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1593556 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1686818 (The Pile)

Max Activating Token Index: 310

Text #18

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.6459. Min Act: -0.0000

Data Index: 430555 (The Pile)

Max Activating Token Index: 872

Text #19

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.6429. Min Act: -0.0000

Data Index: 228776 (The Pile)

Max Activating Token Index: 906