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

Dataset: The Pile

Neuron 2184 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: 1.2319. Min Range: -1.2319

Max Act: 1.2319. Min Act: 0.0000

Data Index: 1973199 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 1.2319. Min Range: -1.2319

Max Act: 1.0746. Min Act: 0.0002

Data Index: 166932 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.2319. Min Range: -1.2319

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1238390 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.9840. Min Act: -0.0000

Data Index: 899039 (The Pile)

Max Activating Token Index: 330

Text #4

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1539226 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1769875 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8936. Min Act: -0.0000

Data Index: 1504621 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8398. Min Act: -0.0000

Data Index: 65135 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1198510 (The Pile)

Max Activating Token Index: 731

Text #9

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8347. Min Act: -0.0000

Data Index: 4589 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1920686 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8536. Min Act: -0.0000

Data Index: 704998 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8488. Min Act: -0.0000

Data Index: 165152 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8724. Min Act: -0.0000

Data Index: 782515 (The Pile)

Max Activating Token Index: 948

Text #14

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8170. Min Act: -0.0000

Data Index: 134813 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1546844 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8122. Min Act: -0.0000

Data Index: 995354 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1932188 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7872. Min Act: -0.0000

Data Index: 320647 (The Pile)

Max Activating Token Index: 652

Text #19

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1937569 (The Pile)

Max Activating Token Index: 365