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

Dataset: The Pile

Neuron 2454 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: 3.5792. Min Range: -3.5792

Max Act: 3.5792. Min Act: -0.0000

Data Index: 1713542 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 3.5792. Min Range: -3.5792

Max Act: 3.5659. Min Act: -0.0000

Data Index: 749968 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 3.5792. Min Range: -3.5792

Max Act: 3.1347. Min Act: -0.0000

Data Index: 496442 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 3.5792. Min Range: -3.5792

Max Act: 3.2132. Min Act: -0.0000

Data Index: 1875294 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 3.5792. Min Range: -3.5792

Max Act: 3.2728. Min Act: -0.0000

Data Index: 96884 (The Pile)

Max Activating Token Index: 862

Text #5

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.9132. Min Act: -0.0000

Data Index: 1195590 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.8968. Min Act: -0.0000

Data Index: 289567 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.7861. Min Act: -0.0000

Data Index: 1316608 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.7715. Min Act: -0.0000

Data Index: 736434 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.0974. Min Act: -0.0000

Data Index: 737784 (The Pile)

Max Activating Token Index: 529

Text #10

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.4222. Min Act: -0.0000

Data Index: 941464 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.3718. Min Act: -0.0000

Data Index: 1505774 (The Pile)

Max Activating Token Index: 657

Text #12

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.3282. Min Act: -0.0000

Data Index: 730218 (The Pile)

Max Activating Token Index: 231

Text #13

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.3233. Min Act: -0.0000

Data Index: 1615837 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.4853. Min Act: -0.0000

Data Index: 1781640 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.1594. Min Act: -0.0000

Data Index: 1248598 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.3005. Min Act: -0.0000

Data Index: 1476622 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.0396. Min Act: -0.0000

Data Index: 1080300 (The Pile)

Max Activating Token Index: 840

Text #18

Max Range: 3.5792. Min Range: -3.5792

Max Act: 2.1265. Min Act: -0.0000

Data Index: 1584182 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 3.5792. Min Range: -3.5792

Max Act: 1.5420. Min Act: -0.0000

Data Index: 1764477 (The Pile)

Max Activating Token Index: 867