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

Dataset: The Pile

Neuron 643 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: 0.8827. Min Range: -0.8827

Max Act: 0.8827. Min Act: -0.0000

Data Index: 560535 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1400596 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7129. Min Act: -0.0000

Data Index: 45623 (The Pile)

Max Activating Token Index: 382

Text #3

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1988799 (The Pile)

Max Activating Token Index: 570

Text #4

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1032454 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6424. Min Act: -0.0000

Data Index: 462023 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1159337 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6468. Min Act: -0.0000

Data Index: 76525 (The Pile)

Max Activating Token Index: 918

Text #8

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1967836 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1649846 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1828296 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6322. Min Act: -0.0000

Data Index: 101284 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6616. Min Act: -0.0000

Data Index: 591293 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1574313 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.4982. Min Act: -0.0000

Data Index: 787165 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.5947. Min Act: -0.0000

Data Index: 693193 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.4921. Min Act: -0.0000

Data Index: 911367 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.5551. Min Act: -0.0000

Data Index: 741692 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1494082 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 0.8827. Min Range: -0.8827

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1085358 (The Pile)

Max Activating Token Index: 345