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

Dataset: The Pile

Neuron 147 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: 1.0885. Min Range: -1.0885

Max Act: 1.0066. Min Act: -0.0000

Data Index: 1371403 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 1.0885. Min Range: -1.0885

Max Act: 1.0885. Min Act: -0.0000

Data Index: 401268 (The Pile)

Max Activating Token Index: 829

Text #2

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1570427 (The Pile)

Max Activating Token Index: 970

Text #3

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8294. Min Act: 0.0000

Data Index: 1163829 (The Pile)

Max Activating Token Index: 843

Text #4

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8617. Min Act: -0.0000

Data Index: 774316 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1714814 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8002. Min Act: 0.0000

Data Index: 1113361 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1974580 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1498091 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.8099. Min Act: -0.0000

Data Index: 708382 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.6578. Min Act: -0.0000

Data Index: 472919 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1793057 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1142775 (The Pile)

Max Activating Token Index: 330

Text #13

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1629747 (The Pile)

Max Activating Token Index: 794

Text #14

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7055. Min Act: -0.0000

Data Index: 962081 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7046. Min Act: -0.0000

Data Index: 197473 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7045. Min Act: -0.0000

Data Index: 133080 (The Pile)

Max Activating Token Index: 594

Text #17

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7263. Min Act: -0.0000

Data Index: 36273 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7466. Min Act: -0.0000

Data Index: 394207 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1457147 (The Pile)

Max Activating Token Index: 760