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

Dataset: The Pile

Neuron 1473 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: 0.5038. Min Range: -0.5038

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1893781 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4259. Min Act: -0.0000

Data Index: 157726 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1614792 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1903581 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3524. Min Act: -0.0000

Data Index: 766361 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3367. Min Act: -0.0000

Data Index: 479144 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3330. Min Act: -0.0000

Data Index: 482794 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1882427 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3316. Min Act: -0.0000

Data Index: 203635 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1655119 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3427. Min Act: -0.0000

Data Index: 544581 (The Pile)

Max Activating Token Index: 682

Text #11

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3191. Min Act: -0.0000

Data Index: 779154 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3629. Min Act: -0.0000

Data Index: 654496 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1894004 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1824937 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3160. Min Act: -0.0000

Data Index: 95983 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1417629 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1615993 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1725558 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1302163 (The Pile)

Max Activating Token Index: 76