Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3526 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1239749 (The Pile)

Max Activating Token Index: 74

Text #1

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2107. Min Act: -0.0000

Data Index: 218927 (The Pile)

Max Activating Token Index: 298

Text #2

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2170. Min Act: -0.0000

Data Index: 677815 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1882757 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1062416 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2032. Min Act: -0.0000

Data Index: 349109 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1831. Min Act: -0.0000

Data Index: 370994 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1792887 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1686122 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1608. Min Act: -0.0000

Data Index: 925709 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1639872 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1840560 (The Pile)

Max Activating Token Index: 636

Text #12

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1679. Min Act: -0.0000

Data Index: 161826 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1596. Min Act: -0.0000

Data Index: 344213 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1687970 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1395. Min Act: -0.0000

Data Index: 827890 (The Pile)

Max Activating Token Index: 688

Text #16

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1857973 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1572. Min Act: -0.0000

Data Index: 234141 (The Pile)

Max Activating Token Index: 259

Text #18

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1549. Min Act: -0.0000

Data Index: 235838 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1396. Min Act: -0.0000

Data Index: 517758 (The Pile)

Max Activating Token Index: 947