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

Dataset: The Pile

Neuron 256 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: 0.1194. Min Range: -0.1194

Max Act: 0.1194. Min Act: -0.0000

Data Index: 695314 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1040. Min Act: -0.0000

Data Index: 685682 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0980. Min Act: -0.0000

Data Index: 72952 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0906. Min Act: -0.0000

Data Index: 879405 (The Pile)

Max Activating Token Index: 653

Text #4

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0898. Min Act: -0.0000

Data Index: 954042 (The Pile)

Max Activating Token Index: 817

Text #5

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1003. Min Act: -0.0000

Data Index: 661616 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1724135 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0802. Min Act: -0.0000

Data Index: 639743 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1878793 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0780. Min Act: -0.0000

Data Index: 451085 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0837. Min Act: -0.0000

Data Index: 155899 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0741. Min Act: -0.0000

Data Index: 1145884 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1060328 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0649. Min Act: -0.0000

Data Index: 523974 (The Pile)

Max Activating Token Index: 547

Text #14

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1349934 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0691. Min Act: -0.0000

Data Index: 546934 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1212164 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0619. Min Act: -0.0000

Data Index: 1247685 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1463520 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0693. Min Act: -0.0000

Data Index: 927555 (The Pile)

Max Activating Token Index: 83