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

Dataset: The Pile

Neuron 1731 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1469920 (The Pile)

Max Activating Token Index: 766

Text #1

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1184. Min Act: -0.0000

Data Index: 964890 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1578316 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1258131 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1028. Min Act: -0.0000

Data Index: 487046 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1553429 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0925. Min Act: -0.0000

Data Index: 999796 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0831. Min Act: -0.0000

Data Index: 460782 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1835808 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1137145 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1635375 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1242906 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0769. Min Act: -0.0000

Data Index: 510908 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1699174 (The Pile)

Max Activating Token Index: 75

Text #14

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0715. Min Act: -0.0000

Data Index: 283837 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0750. Min Act: -0.0000

Data Index: 955795 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1522437 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1197252 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0716. Min Act: -0.0000

Data Index: 818257 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0716. Min Act: -0.0000

Data Index: 590944 (The Pile)

Max Activating Token Index: 29