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

Dataset: The Pile

Neuron 176 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: 0.8490. Min Range: -0.8490

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1348071 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1627534 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1652842 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1361115 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1148418 (The Pile)

Max Activating Token Index: 790

Text #5

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7965. Min Act: -0.0000

Data Index: 800395 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7941. Min Act: -0.0000

Data Index: 95065 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7695. Min Act: -0.0000

Data Index: 939157 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7596. Min Act: -0.0000

Data Index: 185895 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7146. Min Act: -0.0000

Data Index: 960468 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1324045 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1473333 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7265. Min Act: -0.0000

Data Index: 484153 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7450. Min Act: -0.0000

Data Index: 869973 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7245. Min Act: -0.0000

Data Index: 771380 (The Pile)

Max Activating Token Index: 569

Text #15

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1589242 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1036310 (The Pile)

Max Activating Token Index: 778

Text #17

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1270441 (The Pile)

Max Activating Token Index: 429

Text #18

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1235306 (The Pile)

Max Activating Token Index: 778

Text #19

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7408. Min Act: -0.0000

Data Index: 574077 (The Pile)

Max Activating Token Index: 607