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

Dataset: The Pile

Neuron 954 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.9028. Min Act: -0.0000

Data Index: 223792 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.9821. Min Act: -0.0000

Data Index: 568566 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.8638. Min Act: -0.0000

Data Index: 1054919 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.8495. Min Act: -0.0000

Data Index: 1803299 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.7337. Min Act: -0.0000

Data Index: 756820 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.7321. Min Act: -0.0000

Data Index: 1089345 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.6099. Min Act: -0.0000

Data Index: 1558738 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.4999. Min Act: -0.0000

Data Index: 1455531 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.4965. Min Act: -0.0000

Data Index: 345617 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.5865. Min Act: -0.0000

Data Index: 1608698 (The Pile)

Max Activating Token Index: 860

Text #10

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.5392. Min Act: -0.0000

Data Index: 217198 (The Pile)

Max Activating Token Index: 722

Text #11

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.5521. Min Act: -0.0000

Data Index: 921241 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.5343. Min Act: -0.0000

Data Index: 535611 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.5126. Min Act: -0.0000

Data Index: 922646 (The Pile)

Max Activating Token Index: 829

Text #14

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.6920. Min Act: -0.0000

Data Index: 890055 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.4844. Min Act: -0.0000

Data Index: 820437 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1470018 (The Pile)

Max Activating Token Index: 841

Text #17

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.5914. Min Act: -0.0000

Data Index: 1953670 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.4675. Min Act: -0.0000

Data Index: 538988 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.5506. Min Act: -0.0000

Data Index: 1366023 (The Pile)

Max Activating Token Index: 936