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

Dataset: The Pile

Neuron 1881 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: 1.5398. Min Range: -1.5398

Max Act: 1.5398. Min Act: -0.0000

Data Index: 1597582 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.5093. Min Act: -0.0000

Data Index: 1828677 (The Pile)

Max Activating Token Index: 598

Text #2

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.4608. Min Act: -0.0000

Data Index: 1024542 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3357. Min Act: -0.0000

Data Index: 891237 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3829. Min Act: -0.0000

Data Index: 1452876 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3758. Min Act: -0.0000

Data Index: 268749 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3601. Min Act: -0.0000

Data Index: 322396 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1581957 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3936. Min Act: -0.0000

Data Index: 584164 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3511. Min Act: -0.0000

Data Index: 350339 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.4477. Min Act: -0.0000

Data Index: 1702401 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.4121. Min Act: -0.0000

Data Index: 1259791 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3651. Min Act: -0.0000

Data Index: 1558145 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.2584. Min Act: -0.0000

Data Index: 1097640 (The Pile)

Max Activating Token Index: 438

Text #14

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3555. Min Act: -0.0000

Data Index: 960108 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1217667 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1314457 (The Pile)

Max Activating Token Index: 708

Text #17

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3724. Min Act: -0.0000

Data Index: 257478 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.4019. Min Act: -0.0000

Data Index: 627504 (The Pile)

Max Activating Token Index: 436

Text #19

Max Range: 1.5398. Min Range: -1.5398

Max Act: 1.3596. Min Act: -0.0000

Data Index: 1948333 (The Pile)

Max Activating Token Index: 327