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

Dataset: The Pile

Neuron 294 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.3590. Min Act: -0.0000

Data Index: 513074 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1299147 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1438776 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.3990. Min Act: -0.0000

Data Index: 848387 (The Pile)

Max Activating Token Index: 821

Text #4

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.0252. Min Act: -0.0000

Data Index: 752024 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.0408. Min Act: -0.0000

Data Index: 1004435 (The Pile)

Max Activating Token Index: 878

Text #6

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.0703. Min Act: -0.0000

Data Index: 1853107 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1622448 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.0004. Min Act: -0.0000

Data Index: 674082 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1012742 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.0372. Min Act: -0.0000

Data Index: 1199131 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1185649 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.1645. Min Act: -0.0000

Data Index: 1469083 (The Pile)

Max Activating Token Index: 934

Text #13

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.9569. Min Act: -0.0000

Data Index: 75330 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1575269 (The Pile)

Max Activating Token Index: 408

Text #15

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8603. Min Act: -0.0000

Data Index: 508405 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1650088 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.9386. Min Act: -0.0000

Data Index: 840294 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.9257. Min Act: -0.0000

Data Index: 379476 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1950254 (The Pile)

Max Activating Token Index: 104