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

Dataset: The Pile

Neuron 765 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.6275. Min Act: -0.0000

Data Index: 1024684 (The Pile)

Max Activating Token Index: 707

Text #1

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.1474. Min Act: -0.0000

Data Index: 112598 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.2863. Min Act: -0.0000

Data Index: 22925 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1147936 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.1288. Min Act: -0.0000

Data Index: 256957 (The Pile)

Max Activating Token Index: 95

Text #5

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.1346. Min Act: -0.0000

Data Index: 637147 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.0902. Min Act: -0.0000

Data Index: 390983 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.1324. Min Act: -0.0000

Data Index: 967940 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.0792. Min Act: -0.0000

Data Index: 241671 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.0618. Min Act: -0.0000

Data Index: 759159 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.0037. Min Act: -0.0000

Data Index: 791973 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1455660 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1533404 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.6275. Min Range: -1.6275

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1558425 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.0337. Min Act: -0.0000

Data Index: 583570 (The Pile)

Max Activating Token Index: 153

Text #15

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1833544 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 1.6275. Min Range: -1.6275

Max Act: 0.9035. Min Act: -0.0000

Data Index: 918605 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 1.6275. Min Range: -1.6275

Max Act: 1.0142. Min Act: -0.0000

Data Index: 889152 (The Pile)

Max Activating Token Index: 945

Text #18

Max Range: 1.6275. Min Range: -1.6275

Max Act: 0.9468. Min Act: -0.0000

Data Index: 786944 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 1.6275. Min Range: -1.6275

Max Act: 0.9429. Min Act: -0.0000

Data Index: 610792 (The Pile)

Max Activating Token Index: 824