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

Dataset: The Pile

Neuron 1537 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: 0.8835. Min Range: -0.8835

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1255321 (The Pile)

Max Activating Token Index: 251

Text #1

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8667. Min Act: -0.0000

Data Index: 257699 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7793. Min Act: -0.0000

Data Index: 225426 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8170. Min Act: -0.0000

Data Index: 49823 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1303365 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7526. Min Act: -0.0000

Data Index: 775606 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1390796 (The Pile)

Max Activating Token Index: 869

Text #7

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1731249 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7048. Min Act: -0.0000

Data Index: 795761 (The Pile)

Max Activating Token Index: 72

Text #9

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6633. Min Act: -0.0000

Data Index: 620563 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7091. Min Act: -0.0000

Data Index: 22444 (The Pile)

Max Activating Token Index: 11

Text #11

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1524630 (The Pile)

Max Activating Token Index: 127

Text #12

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7047. Min Act: -0.0000

Data Index: 855561 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6990. Min Act: -0.0000

Data Index: 417601 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1651968 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1408012 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1854706 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6513. Min Act: -0.0000

Data Index: 899411 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1321865 (The Pile)

Max Activating Token Index: 389

Text #19

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6151. Min Act: -0.0000

Data Index: 846753 (The Pile)

Max Activating Token Index: 190