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

Dataset: The Pile

Neuron 1125 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0477. Min Act: -0.0000

Data Index: 311672 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0452. Min Act: -0.0000

Data Index: 984066 (The Pile)

Max Activating Token Index: 840

Text #2

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0420. Min Act: -0.0000

Data Index: 859106 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0447. Min Act: -0.0000

Data Index: 371501 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0414. Min Act: -0.0000

Data Index: 456945 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0461. Min Act: -0.0000

Data Index: 44931 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1791806 (The Pile)

Max Activating Token Index: 521

Text #7

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0400. Min Act: -0.0000

Data Index: 1023617 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1934668 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1476291 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0390. Min Act: -0.0000

Data Index: 426740 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0415. Min Act: -0.0000

Data Index: 562697 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1054632 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1707847 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1094513 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0406. Min Act: -0.0000

Data Index: 878530 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1694070 (The Pile)

Max Activating Token Index: 778

Text #17

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1064576 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1763460 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0409. Min Act: -0.0000

Data Index: 129614 (The Pile)

Max Activating Token Index: 303