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

Dataset: The Pile

Neuron 116 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.1689. Min Act: -0.0000

Data Index: 1495785 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.1281. Min Act: -0.0000

Data Index: 823217 (The Pile)

Max Activating Token Index: 530

Text #2

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1303767 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.0419. Min Act: -0.0000

Data Index: 1298064 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1902461 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.0036. Min Act: -0.0000

Data Index: 1510314 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.0042. Min Act: -0.0000

Data Index: 476140 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9800. Min Act: -0.0000

Data Index: 424093 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1347711 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9886. Min Act: -0.0000

Data Index: 1112568 (The Pile)

Max Activating Token Index: 651

Text #10

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9487. Min Act: -0.0000

Data Index: 457309 (The Pile)

Max Activating Token Index: 643

Text #11

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9680. Min Act: -0.0000

Data Index: 132588 (The Pile)

Max Activating Token Index: 840

Text #12

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1815085 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9832. Min Act: -0.0000

Data Index: 621714 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1159007 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1484670 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9746. Min Act: -0.0000

Data Index: 752252 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9327. Min Act: -0.0000

Data Index: 313452 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1398237 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9252. Min Act: -0.0000

Data Index: 462111 (The Pile)

Max Activating Token Index: 728