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

Dataset: The Pile

Neuron 2909 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: 0.8373. Min Range: -0.8373

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1662196 (The Pile)

Max Activating Token Index: 11

Text #1

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1347550 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.8325. Min Act: -0.0000

Data Index: 258704 (The Pile)

Max Activating Token Index: 391

Text #3

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.8322. Min Act: -0.0000

Data Index: 715114 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.8166. Min Act: -0.0000

Data Index: 825617 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1231432 (The Pile)

Max Activating Token Index: 11

Text #6

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1618103 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1936874 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6922. Min Act: -0.0000

Data Index: 503260 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6569. Min Act: -0.0000

Data Index: 876243 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1189812 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1642283 (The Pile)

Max Activating Token Index: 955

Text #12

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1727906 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1746583 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1910625 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6788. Min Act: -0.0000

Data Index: 253916 (The Pile)

Max Activating Token Index: 377

Text #16

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1825918 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7566. Min Act: -0.0000

Data Index: 273711 (The Pile)

Max Activating Token Index: 478

Text #18

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1869157 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1117384 (The Pile)

Max Activating Token Index: 230