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

Dataset: The Pile

Neuron 3586 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: 1.0829. Min Range: -1.0829

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1442543 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1549236 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1688683 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1107320 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1167548 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6601. Min Act: -0.0000

Data Index: 138890 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1287030 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1278976 (The Pile)

Max Activating Token Index: 312

Text #8

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1976998 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1572273 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1762481 (The Pile)

Max Activating Token Index: 38

Text #11

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1586499 (The Pile)

Max Activating Token Index: 3

Text #12

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1553899 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.5927. Min Act: -0.0000

Data Index: 372884 (The Pile)

Max Activating Token Index: 729

Text #14

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1187591 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1056191 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1056370 (The Pile)

Max Activating Token Index: 318

Text #17

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.5616. Min Act: -0.0000

Data Index: 923400 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1562922 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.5418. Min Act: -0.0000

Data Index: 928890 (The Pile)

Max Activating Token Index: 291