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

Dataset: The Pile

Neuron 4567 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: 0.8945. Min Range: -0.8945

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1786132 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1754832 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7689. Min Act: -0.0000

Data Index: 177853 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1992855 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7306. Min Act: -0.0000

Data Index: 325642 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1283873 (The Pile)

Max Activating Token Index: 266

Text #6

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1351295 (The Pile)

Max Activating Token Index: 792

Text #7

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7720. Min Act: -0.0000

Data Index: 876750 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7447. Min Act: -0.0000

Data Index: 271851 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1096517 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7328. Min Act: -0.0000

Data Index: 803744 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7013. Min Act: -0.0000

Data Index: 241893 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7537. Min Act: -0.0000

Data Index: 139131 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7044. Min Act: -0.0000

Data Index: 228549 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.6745. Min Act: -0.0000

Data Index: 876912 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.6829. Min Act: -0.0000

Data Index: 257097 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.6781. Min Act: -0.0000

Data Index: 886629 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.6704. Min Act: -0.0000

Data Index: 553165 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.6096. Min Act: -0.0000

Data Index: 870106 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.6738. Min Act: -0.0000

Data Index: 205698 (The Pile)

Max Activating Token Index: 334