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

Dataset: The Pile

Neuron 1487 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.8080. Min Act: -0.0001

Data Index: 1559796 (The Pile)

Max Activating Token Index: 298

Text #1

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7370. Min Act: -0.0000

Data Index: 975845 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7859. Min Act: -0.0001

Data Index: 586059 (The Pile)

Max Activating Token Index: 714

Text #3

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7248. Min Act: -0.0000

Data Index: 178567 (The Pile)

Max Activating Token Index: 122

Text #4

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6759. Min Act: -0.0001

Data Index: 46820 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7104. Min Act: -0.0001

Data Index: 1971055 (The Pile)

Max Activating Token Index: 969

Text #6

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7276. Min Act: -0.0001

Data Index: 995485 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1789814 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6884. Min Act: -0.0000

Data Index: 734269 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7350. Min Act: -0.0001

Data Index: 111560 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7608. Min Act: -0.0001

Data Index: 54510 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7366. Min Act: -0.0001

Data Index: 270254 (The Pile)

Max Activating Token Index: 715

Text #12

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6979. Min Act: -0.0001

Data Index: 1575937 (The Pile)

Max Activating Token Index: 841

Text #13

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7185. Min Act: -0.0001

Data Index: 488710 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6777. Min Act: -0.0001

Data Index: 655410 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6836. Min Act: -0.0000

Data Index: 16127 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6990. Min Act: -0.0001

Data Index: 1407082 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6876. Min Act: -0.0001

Data Index: 1438185 (The Pile)

Max Activating Token Index: 531

Text #18

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6750. Min Act: -0.0001

Data Index: 1624401 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1789136 (The Pile)

Max Activating Token Index: 796