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

Dataset: The Pile

Neuron 1609 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0640. Min Act: 0.0000

Data Index: 1196490 (The Pile)

Max Activating Token Index: 712

Text #1

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1512765 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1813892 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 1.1507. Min Range: -1.1507

Max Act: 1.0486. Min Act: -0.0000

Data Index: 107562 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1711795 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8628. Min Act: -0.0000

Data Index: 798523 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8229. Min Act: -0.0000

Data Index: 532741 (The Pile)

Max Activating Token Index: 791

Text #7

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8827. Min Act: -0.0000

Data Index: 167580 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1434759 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.6712. Min Act: 0.0000

Data Index: 871462 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7846. Min Act: -0.0000

Data Index: 13568 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1370808 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1516462 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7885. Min Act: -0.0000

Data Index: 757731 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7365. Min Act: -0.0000

Data Index: 221973 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7103. Min Act: -0.0000

Data Index: 873915 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1513000 (The Pile)

Max Activating Token Index: 979

Text #17

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1896487 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1082429 (The Pile)

Max Activating Token Index: 721

Text #19

Max Range: 1.1507. Min Range: -1.1507

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1439816 (The Pile)

Max Activating Token Index: 659