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

Dataset: The Pile

Neuron 11 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2420. Min Act: -0.0000

Data Index: 482987 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2390. Min Act: -0.0000

Data Index: 542948 (The Pile)

Max Activating Token Index: 456

Text #2

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2298. Min Act: -0.0000

Data Index: 808196 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1127533 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1982. Min Act: -0.0000

Data Index: 444287 (The Pile)

Max Activating Token Index: 454

Text #5

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1899017 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1956. Min Act: -0.0000

Data Index: 106123 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1879. Min Act: -0.0000

Data Index: 621124 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1855183 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1858. Min Act: -0.0000

Data Index: 678125 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1185996 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1808. Min Act: -0.0000

Data Index: 432212 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1352414 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1792. Min Act: -0.0000

Data Index: 75571 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1051477 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1437549 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1609317 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1364845 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1760. Min Act: -0.0000

Data Index: 964320 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1142216 (The Pile)

Max Activating Token Index: 682