Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2331 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0376. Min Range: -1.0376

Max Act: 1.0219. Min Act: -0.0000

Data Index: 259983 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 1.0376. Min Range: -1.0376

Max Act: 1.0376. Min Act: -0.0000

Data Index: 854722 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.9059. Min Act: -0.0000

Data Index: 644214 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.9265. Min Act: -0.0000

Data Index: 664093 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1394373 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8555. Min Act: -0.0000

Data Index: 985664 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7818. Min Act: -0.0000

Data Index: 8369 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8843. Min Act: -0.0000

Data Index: 738572 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1555151 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6920. Min Act: -0.0000

Data Index: 701984 (The Pile)

Max Activating Token Index: 220

Text #10

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1878799 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.8024. Min Act: -0.0000

Data Index: 46855 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1138434 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7034. Min Act: -0.0000

Data Index: 260508 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6728. Min Act: -0.0000

Data Index: 559739 (The Pile)

Max Activating Token Index: 666

Text #15

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1798854 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1099397 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6622. Min Act: -0.0000

Data Index: 613761 (The Pile)

Max Activating Token Index: 261

Text #18

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6689. Min Act: -0.0000

Data Index: 930208 (The Pile)

Max Activating Token Index: 129

Text #19

Max Range: 1.0376. Min Range: -1.0376

Max Act: 0.6971. Min Act: -0.0000

Data Index: 38525 (The Pile)

Max Activating Token Index: 28