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

Dataset: The Pile

Neuron 1931 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0943. Min Act: -0.0000

Data Index: 529713 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1890748 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0921. Min Act: -0.0000

Data Index: 930025 (The Pile)

Max Activating Token Index: 896

Text #3

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1339149 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1252724 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1779771 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1525692 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9769. Min Act: -0.0000

Data Index: 454103 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9507. Min Act: -0.0000

Data Index: 970891 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0150. Min Act: -0.0000

Data Index: 127096 (The Pile)

Max Activating Token Index: 707

Text #10

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9434. Min Act: -0.0000

Data Index: 262188 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1034492 (The Pile)

Max Activating Token Index: 641

Text #12

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1579818 (The Pile)

Max Activating Token Index: 819

Text #13

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9585. Min Act: -0.0000

Data Index: 21533 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1635347 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1414387 (The Pile)

Max Activating Token Index: 248

Text #16

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1494522 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9177. Min Act: -0.0000

Data Index: 926058 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9415. Min Act: -0.0000

Data Index: 935361 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1419258 (The Pile)

Max Activating Token Index: 921