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

Dataset: The Pile

Neuron 1283 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.7467. Min Act: -0.0000

Data Index: 975318 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1396737 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1820347 (The Pile)

Max Activating Token Index: 497

Text #3

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1454042 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6368. Min Act: -0.0000

Data Index: 534181 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1296112 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1988183 (The Pile)

Max Activating Token Index: 243

Text #7

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1272680 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1385603 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5720. Min Act: -0.0000

Data Index: 379384 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1586706 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1293894 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5688. Min Act: -0.0000

Data Index: 826363 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1795083 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1870728 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1458918 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1146396 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.4821. Min Act: 0.0001

Data Index: 1186820 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5413. Min Act: -0.0000

Data Index: 599068 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5580. Min Act: -0.0000

Data Index: 456230 (The Pile)

Max Activating Token Index: 593