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

Dataset: The Pile

Neuron 3719 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1926337 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1278530 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1361681 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4661. Min Act: -0.0000

Data Index: 894292 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4649. Min Act: -0.0000

Data Index: 245686 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1822036 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1678822 (The Pile)

Max Activating Token Index: 660

Text #7

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1620877 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1569350 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4455. Min Act: -0.0000

Data Index: 348154 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1844602 (The Pile)

Max Activating Token Index: 168

Text #11

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4144. Min Act: -0.0000

Data Index: 828479 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3957. Min Act: -0.0000

Data Index: 355567 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3637. Min Act: -0.0000

Data Index: 460368 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3819. Min Act: -0.0000

Data Index: 320129 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3861. Min Act: -0.0000

Data Index: 668801 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3851. Min Act: -0.0000

Data Index: 921980 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3824. Min Act: -0.0000

Data Index: 722190 (The Pile)

Max Activating Token Index: 645

Text #18

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1873377 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3964. Min Act: -0.0000

Data Index: 240979 (The Pile)

Max Activating Token Index: 866