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

Dataset: The Pile

Neuron 3905 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: 0.8876. Min Range: -0.8876

Max Act: 0.8876. Min Act: -0.0000

Data Index: 765001 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6397. Min Act: -0.0000

Data Index: 927307 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6490. Min Act: -0.0000

Data Index: 849313 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6165. Min Act: -0.0000

Data Index: 86512 (The Pile)

Max Activating Token Index: 453

Text #4

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6556. Min Act: -0.0000

Data Index: 259897 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6863. Min Act: -0.0000

Data Index: 858751 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1011777 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6231. Min Act: -0.0000

Data Index: 235745 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.4767. Min Act: -0.0000

Data Index: 712169 (The Pile)

Max Activating Token Index: 968

Text #9

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.5190. Min Act: -0.0000

Data Index: 187268 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.4681. Min Act: -0.0000

Data Index: 881682 (The Pile)

Max Activating Token Index: 942

Text #11

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1273792 (The Pile)

Max Activating Token Index: 652

Text #12

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.4973. Min Act: -0.0000

Data Index: 583207 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1509997 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1227404 (The Pile)

Max Activating Token Index: 643

Text #15

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1504401 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1524655 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1782627 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1425163 (The Pile)

Max Activating Token Index: 779

Text #19

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1910845 (The Pile)

Max Activating Token Index: 786