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

Dataset: The Pile

Neuron 2725 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: 1.1013. Min Range: -1.1013

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1645237 (The Pile)

Max Activating Token Index: 662

Text #1

Max Range: 1.1013. Min Range: -1.1013

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1528887 (The Pile)

Max Activating Token Index: 353

Text #2

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1311096 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.9819. Min Act: 0.0000

Data Index: 260549 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1125224 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1268664 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1336012 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8277. Min Act: -0.0000

Data Index: 883982 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8142. Min Act: -0.0000

Data Index: 182306 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8041. Min Act: 0.0000

Data Index: 591123 (The Pile)

Max Activating Token Index: 273

Text #10

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7605. Min Act: -0.0000

Data Index: 140698 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7835. Min Act: -0.0000

Data Index: 448948 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1813085 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8409. Min Act: -0.0000

Data Index: 218009 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7696. Min Act: -0.0000

Data Index: 426325 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1643305 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1162075 (The Pile)

Max Activating Token Index: 89

Text #17

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7575. Min Act: -0.0000

Data Index: 760886 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7660. Min Act: -0.0000

Data Index: 305075 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7362. Min Act: -0.0000

Data Index: 723988 (The Pile)

Max Activating Token Index: 1021