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

Dataset: The Pile

Neuron 3784 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1416443 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1966795 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.1719. Min Act: -0.0000

Data Index: 129907 (The Pile)

Max Activating Token Index: 357

Text #3

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0546. Min Act: -0.0000

Data Index: 834759 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1781034 (The Pile)

Max Activating Token Index: 610

Text #5

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1056050 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.9363. Min Act: -0.0000

Data Index: 281632 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1947168 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 1.2066. Min Range: -1.2066

Max Act: 1.0984. Min Act: -0.0000

Data Index: 809285 (The Pile)

Max Activating Token Index: 969

Text #9

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1706493 (The Pile)

Max Activating Token Index: 929

Text #10

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.9633. Min Act: -0.0000

Data Index: 947555 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1401901 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.8617. Min Act: -0.0000

Data Index: 123627 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1028497 (The Pile)

Max Activating Token Index: 289

Text #14

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.8421. Min Act: -0.0000

Data Index: 287689 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1493152 (The Pile)

Max Activating Token Index: 690

Text #16

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1877550 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.8581. Min Act: -0.0000

Data Index: 558517 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1619915 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 1.2066. Min Range: -1.2066

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1643836 (The Pile)

Max Activating Token Index: 67