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

Dataset: The Pile

Neuron 1895 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.8004. Min Act: -0.0000

Data Index: 698559 (The Pile)

Max Activating Token Index: 251

Text #1

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1495428 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7518. Min Act: -0.0000

Data Index: 87441 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7276. Min Act: -0.0000

Data Index: 130548 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1315987 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1877016 (The Pile)

Max Activating Token Index: 368

Text #6

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.8258. Min Act: -0.0000

Data Index: 344287 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1650077 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6227. Min Act: -0.0000

Data Index: 616566 (The Pile)

Max Activating Token Index: 811

Text #9

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1393539 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7047. Min Act: 0.0001

Data Index: 1326647 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6872. Min Act: 0.0000

Data Index: 1240318 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7408. Min Act: -0.0000

Data Index: 372772 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1984075 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1157303 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6947. Min Act: -0.0000

Data Index: 350474 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1447575 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6464. Min Act: -0.0000

Data Index: 689016 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1014926 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.5761. Min Act: -0.0000

Data Index: 517116 (The Pile)

Max Activating Token Index: 190