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

Dataset: The Pile

Neuron 3007 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: 1.1046. Min Range: -1.1046

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1212899 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 1.1046. Min Range: -1.1046

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1129583 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1218892 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1827901 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8745. Min Act: -0.0000

Data Index: 443528 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1972384 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8430. Min Act: -0.0000

Data Index: 388835 (The Pile)

Max Activating Token Index: 254

Text #7

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9112. Min Act: -0.0000

Data Index: 962604 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8025. Min Act: -0.0000

Data Index: 830940 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1030542 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1257096 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1040918 (The Pile)

Max Activating Token Index: 355

Text #12

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.6861. Min Act: -0.0000

Data Index: 474578 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8241. Min Act: -0.0000

Data Index: 304789 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8154. Min Act: -0.0000

Data Index: 747311 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7995. Min Act: -0.0000

Data Index: 846306 (The Pile)

Max Activating Token Index: 306

Text #16

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7988. Min Act: -0.0000

Data Index: 873468 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1470072 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8317. Min Act: -0.0000

Data Index: 290659 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1187225 (The Pile)

Max Activating Token Index: 609