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

Dataset: The Pile

Neuron 1387 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6556. Min Act: -0.0000

Data Index: 503616 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.8338. Min Act: -0.0000

Data Index: 1884810 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6420. Min Act: -0.0000

Data Index: 458533 (The Pile)

Max Activating Token Index: 874

Text #3

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6824. Min Act: -0.0000

Data Index: 667403 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6932. Min Act: -0.0000

Data Index: 1712597 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.5955. Min Act: -0.0000

Data Index: 109870 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6932. Min Act: -0.0000

Data Index: 1321819 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7598. Min Act: -0.0000

Data Index: 555260 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.5607. Min Act: -0.0000

Data Index: 1599056 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.5557. Min Act: -0.0000

Data Index: 1747984 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.4417. Min Act: -0.0000

Data Index: 869044 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.4413. Min Act: -0.0000

Data Index: 1862685 (The Pile)

Max Activating Token Index: 334

Text #12

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.5311. Min Act: -0.0000

Data Index: 235784 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.5108. Min Act: -0.0000

Data Index: 1606131 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.5932. Min Act: -0.0000

Data Index: 1374014 (The Pile)

Max Activating Token Index: 751

Text #15

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.3759. Min Act: -0.0000

Data Index: 209681 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.3019. Min Act: -0.0000

Data Index: 178167 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.3673. Min Act: -0.0000

Data Index: 536600 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1277939 (The Pile)

Max Activating Token Index: 379

Text #19

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.4035. Min Act: -0.0000

Data Index: 668129 (The Pile)

Max Activating Token Index: 1019