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

Dataset: The Pile

Neuron 4304 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: 1.1216. Min Range: -1.1216

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1842748 (The Pile)

Max Activating Token Index: 314

Text #1

Max Range: 1.1216. Min Range: -1.1216

Max Act: 1.1216. Min Act: -0.0000

Data Index: 574715 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 1.1216. Min Range: -1.1216

Max Act: 1.0742. Min Act: -0.0000

Data Index: 624673 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9977. Min Act: -0.0000

Data Index: 561142 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 1.1216. Min Range: -1.1216

Max Act: 1.0556. Min Act: -0.0000

Data Index: 615690 (The Pile)

Max Activating Token Index: 340

Text #5

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1090926 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.1216. Min Range: -1.1216

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1744795 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9475. Min Act: -0.0000

Data Index: 767898 (The Pile)

Max Activating Token Index: 228

Text #8

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1106630 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1431697 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9168. Min Act: -0.0000

Data Index: 422701 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1533450 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9056. Min Act: -0.0000

Data Index: 271931 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.7813. Min Act: -0.0000

Data Index: 419274 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1288584 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8155. Min Act: -0.0000

Data Index: 352570 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8972. Min Act: -0.0000

Data Index: 771078 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8614. Min Act: -0.0000

Data Index: 52731 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1311151 (The Pile)

Max Activating Token Index: 956

Text #19

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8706. Min Act: -0.0000

Data Index: 913067 (The Pile)

Max Activating Token Index: 435