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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1595 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.9684. Min Act: -0.0001

Data Index: 841056 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5662. Min Act: -0.0000

Data Index: 136555 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.1690. Min Act: -0.0000

Data Index: 188474 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.1512. Min Act: -0.0000

Data Index: 401435 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.0121. Min Act: -0.0000

Data Index: 627363 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.9504. Min Act: -0.0000

Data Index: 788410 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.0157. Min Act: -0.0001

Data Index: 400125 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1284900 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.9888. Min Act: -0.0000

Data Index: 111951 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.0287. Min Act: -0.0000

Data Index: 377802 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1293814 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.9838. Min Act: -0.0000

Data Index: 949892 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.9500. Min Act: -0.0001

Data Index: 554189 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.9178. Min Act: -0.0000

Data Index: 837100 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.8604. Min Act: -0.0001

Data Index: 1079061 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.9008. Min Act: -0.0000

Data Index: 464382 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1084887 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.8839. Min Act: -0.0001

Data Index: 548303 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.8720. Min Act: -0.0000

Data Index: 579036 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 1.9684. Min Range: -1.9684

Max Act: 0.8979. Min Act: -0.0000

Data Index: 819637 (C4 (Web Text))

Max Activating Token Index: 26