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

Dataset: The Pile

Neuron 564 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.9401. Min Act: -0.0000

Data Index: 279299 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1527084 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8094. Min Act: -0.0000

Data Index: 688363 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8242. Min Act: -0.0000

Data Index: 536872 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1635256 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1017640 (The Pile)

Max Activating Token Index: 192

Text #6

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1423210 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7278. Min Act: -0.0000

Data Index: 128155 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7632. Min Act: -0.0000

Data Index: 475901 (The Pile)

Max Activating Token Index: 362

Text #9

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7110. Min Act: -0.0000

Data Index: 381213 (The Pile)

Max Activating Token Index: 602

Text #10

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1371194 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1885583 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1725104 (The Pile)

Max Activating Token Index: 995

Text #13

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6760. Min Act: -0.0000

Data Index: 506577 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7203. Min Act: -0.0000

Data Index: 954284 (The Pile)

Max Activating Token Index: 749

Text #15

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6686. Min Act: -0.0000

Data Index: 494198 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1111123 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1483535 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1247448 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.5929. Min Act: -0.0000

Data Index: 100009 (The Pile)

Max Activating Token Index: 234