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

Dataset: The Pile

Neuron 3676 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: 0.2491. Min Range: -0.2491

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1099364 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1213496 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1355300 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1887. Min Act: -0.0000

Data Index: 680955 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1082151 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1696. Min Act: -0.0000

Data Index: 331553 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1752. Min Act: -0.0000

Data Index: 56229 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1560358 (The Pile)

Max Activating Token Index: 850

Text #8

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1515. Min Act: -0.0000

Data Index: 896346 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1768032 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1475. Min Act: -0.0000

Data Index: 357060 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1515. Min Act: -0.0000

Data Index: 707191 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1037049 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1653. Min Act: -0.0000

Data Index: 186291 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1897903 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1138245 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1295611 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1609. Min Act: -0.0000

Data Index: 77638 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1218628 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1322907 (The Pile)

Max Activating Token Index: 695