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

Dataset: The Pile

Neuron 2845 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.2867. Min Act: -0.0000

Data Index: 859931 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.4660. Min Act: -0.0000

Data Index: 1703842 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 1.4660. Min Range: -1.4660

Max Act: 0.9236. Min Act: -0.0000

Data Index: 635367 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1538858 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.1277. Min Act: -0.0000

Data Index: 637520 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.0500. Min Act: -0.0000

Data Index: 703797 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.0098. Min Act: -0.0000

Data Index: 332795 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1835542 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.0497. Min Act: -0.0000

Data Index: 1542371 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 1.4660. Min Range: -1.4660

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1419999 (The Pile)

Max Activating Token Index: 950

Text #10

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.0050. Min Act: -0.0000

Data Index: 935705 (The Pile)

Max Activating Token Index: 902

Text #11

Max Range: 1.4660. Min Range: -1.4660

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1438576 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.0233. Min Act: -0.0000

Data Index: 872793 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 1.4660. Min Range: -1.4660

Max Act: 0.8755. Min Act: -0.0000

Data Index: 653746 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 1.4660. Min Range: -1.4660

Max Act: 0.9521. Min Act: -0.0000

Data Index: 212968 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.0498. Min Act: -0.0000

Data Index: 1543940 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 1.4660. Min Range: -1.4660

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1465256 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 1.4660. Min Range: -1.4660

Max Act: 1.0111. Min Act: -0.0000

Data Index: 735183 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 1.4660. Min Range: -1.4660

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1780732 (The Pile)

Max Activating Token Index: 927

Text #19

Max Range: 1.4660. Min Range: -1.4660

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1811632 (The Pile)

Max Activating Token Index: 665