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

Dataset: The Pile

Neuron 2604 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: 0.9904. Min Range: -0.9904

Max Act: 0.9904. Min Act: -0.0000

Data Index: 228448 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1805877 (The Pile)

Max Activating Token Index: 912

Text #2

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8849. Min Act: -0.0000

Data Index: 924383 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8705. Min Act: -0.0000

Data Index: 1903621 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.7711. Min Act: -0.0000

Data Index: 435141 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.7610. Min Act: -0.0000

Data Index: 100088 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1763478 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1377046 (The Pile)

Max Activating Token Index: 351

Text #8

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6709. Min Act: -0.0000

Data Index: 543793 (The Pile)

Max Activating Token Index: 666

Text #9

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.7050. Min Act: -0.0000

Data Index: 284243 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1370599 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1640722 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6569. Min Act: -0.0000

Data Index: 880552 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6702. Min Act: -0.0000

Data Index: 857613 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.5957. Min Act: -0.0000

Data Index: 973753 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6404. Min Act: -0.0000

Data Index: 755418 (The Pile)

Max Activating Token Index: 946

Text #16

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6066. Min Act: -0.0000

Data Index: 160507 (The Pile)

Max Activating Token Index: 719

Text #17

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1523437 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.5812. Min Act: -0.0000

Data Index: 245199 (The Pile)

Max Activating Token Index: 231

Text #19

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1904918 (The Pile)

Max Activating Token Index: 549