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

Dataset: The Pile

Neuron 3309 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: 1.1073. Min Range: -1.1073

Max Act: 1.1073. Min Act: -0.0000

Data Index: 210829 (The Pile)

Max Activating Token Index: 836

Text #1

Max Range: 1.1073. Min Range: -1.1073

Max Act: 1.0186. Min Act: -0.0000

Data Index: 1807039 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9539. Min Act: -0.0000

Data Index: 284848 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9442. Min Act: -0.0000

Data Index: 25950 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1341867 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1173535 (The Pile)

Max Activating Token Index: 182

Text #6

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8801. Min Act: -0.0000

Data Index: 824780 (The Pile)

Max Activating Token Index: 228

Text #7

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9321. Min Act: -0.0000

Data Index: 439891 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1954949 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9004. Min Act: -0.0000

Data Index: 359825 (The Pile)

Max Activating Token Index: 929

Text #10

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9208. Min Act: -0.0000

Data Index: 448824 (The Pile)

Max Activating Token Index: 736

Text #11

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1186399 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1869726 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9082. Min Act: -0.0000

Data Index: 995576 (The Pile)

Max Activating Token Index: 87

Text #14

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9613. Min Act: -0.0000

Data Index: 599494 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9601. Min Act: -0.0000

Data Index: 643980 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8988. Min Act: -0.0000

Data Index: 680866 (The Pile)

Max Activating Token Index: 802

Text #17

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1244998 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1212592 (The Pile)

Max Activating Token Index: 619

Text #19

Max Range: 1.1073. Min Range: -1.1073

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1220546 (The Pile)

Max Activating Token Index: 98