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

Dataset: The Pile

Neuron 4599 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1479688 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1536199 (The Pile)

Max Activating Token Index: 891

Text #2

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3018. Min Act: -0.0000

Data Index: 520182 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1268706 (The Pile)

Max Activating Token Index: 659

Text #4

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1181065 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2932. Min Act: -0.0000

Data Index: 438121 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2792. Min Act: -0.0000

Data Index: 564446 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1440256 (The Pile)

Max Activating Token Index: 376

Text #8

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2611. Min Act: -0.0000

Data Index: 568189 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1852832 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2649. Min Act: -0.0000

Data Index: 517372 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1951049 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1314254 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2651. Min Act: -0.0000

Data Index: 729085 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1512555 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2547. Min Act: -0.0000

Data Index: 811601 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1768853 (The Pile)

Max Activating Token Index: 410

Text #17

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1137127 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1662651 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1448452 (The Pile)

Max Activating Token Index: 633