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

Dataset: The Pile

Neuron 2143 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.3269. Min Act: -0.0000

Data Index: 716352 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.3224. Min Act: -0.0000

Data Index: 933895 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0927. Min Act: -0.0000

Data Index: 642794 (The Pile)

Max Activating Token Index: 23

Text #3

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1353914 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1405511 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1309. Min Act: -0.0000

Data Index: 1213334 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1593. Min Act: -0.0000

Data Index: 352412 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1478. Min Act: -0.0000

Data Index: 711723 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1685. Min Act: -0.0000

Data Index: 775 (The Pile)

Max Activating Token Index: 281

Text #9

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1153307 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0404. Min Act: -0.0000

Data Index: 395643 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1463146 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1005654 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9273. Min Act: -0.0000

Data Index: 897664 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1541210 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9512. Min Act: -0.0000

Data Index: 381704 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1826051 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1520667 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1839800 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1518553 (The Pile)

Max Activating Token Index: 499