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

Dataset: The Pile

Neuron 3695 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: 8.8581. Min Range: -8.8581

Max Act: 8.8581. Min Act: -0.0000

Data Index: 1406880 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 8.8581. Min Range: -8.8581

Max Act: 8.5110. Min Act: -0.0000

Data Index: 1794859 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 8.8581. Min Range: -8.8581

Max Act: 8.3188. Min Act: -0.0000

Data Index: 1713796 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 8.8581. Min Range: -8.8581

Max Act: 8.4606. Min Act: -0.0000

Data Index: 1678923 (The Pile)

Max Activating Token Index: 855

Text #4

Max Range: 8.8581. Min Range: -8.8581

Max Act: 8.2744. Min Act: -0.0000

Data Index: 719996 (The Pile)

Max Activating Token Index: 309

Text #5

Max Range: 8.8581. Min Range: -8.8581

Max Act: 8.0747. Min Act: -0.0000

Data Index: 1198939 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 8.8581. Min Range: -8.8581

Max Act: 8.1182. Min Act: -0.0000

Data Index: 426497 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 8.8581. Min Range: -8.8581

Max Act: 8.0772. Min Act: -0.0000

Data Index: 359562 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.9256. Min Act: -0.0000

Data Index: 1701771 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 8.8581. Min Range: -8.8581

Max Act: 8.2445. Min Act: -0.0000

Data Index: 1238713 (The Pile)

Max Activating Token Index: 249

Text #10

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.8203. Min Act: -0.0000

Data Index: 90445 (The Pile)

Max Activating Token Index: 799

Text #11

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.8983. Min Act: -0.0000

Data Index: 1896172 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.8489. Min Act: -0.0000

Data Index: 621626 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.8043. Min Act: -0.0000

Data Index: 998806 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.8306. Min Act: -0.0000

Data Index: 1098784 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.7502. Min Act: -0.0000

Data Index: 1901495 (The Pile)

Max Activating Token Index: 46

Text #16

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.7074. Min Act: -0.0000

Data Index: 1456604 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.7053. Min Act: -0.0000

Data Index: 1959148 (The Pile)

Max Activating Token Index: 585

Text #18

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.4566. Min Act: -0.0000

Data Index: 1098119 (The Pile)

Max Activating Token Index: 125

Text #19

Max Range: 8.8581. Min Range: -8.8581

Max Act: 7.5655. Min Act: -0.0000

Data Index: 1756080 (The Pile)

Max Activating Token Index: 157