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

Dataset: The Pile

Neuron 3690 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3358. Min Range: -1.3358

Max Act: 1.3358. Min Act: -0.0000

Data Index: 5762 (The Pile)

Max Activating Token Index: 570

Text #1

Max Range: 1.3358. Min Range: -1.3358

Max Act: 1.1679. Min Act: -0.0000

Data Index: 1588686 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 1.3358. Min Range: -1.3358

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1035903 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.3358. Min Range: -1.3358

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1305987 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.9706. Min Act: -0.0000

Data Index: 744882 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.8700. Min Act: -0.0000

Data Index: 389368 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1514800 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.8040. Min Act: -0.0000

Data Index: 200863 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1631148 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1110339 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7644. Min Act: -0.0000

Data Index: 804394 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1798445 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7674. Min Act: -0.0000

Data Index: 832636 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.6767. Min Act: -0.0000

Data Index: 221565 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1615073 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1547339 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7042. Min Act: -0.0000

Data Index: 868173 (The Pile)

Max Activating Token Index: 392

Text #17

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7219. Min Act: -0.0000

Data Index: 322501 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7210. Min Act: -0.0000

Data Index: 924698 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 1.3358. Min Range: -1.3358

Max Act: 0.7368. Min Act: -0.0000

Data Index: 246782 (The Pile)

Max Activating Token Index: 794