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

Dataset: The Pile

Neuron 742 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1450108 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.3227. Min Act: -0.0000

Data Index: 546535 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2980. Min Act: -0.0000

Data Index: 644542 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1151933 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1850154 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2817. Min Act: -0.0000

Data Index: 105179 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.3158. Min Act: -0.0000

Data Index: 206227 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2929. Min Act: -0.0000

Data Index: 633799 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2765. Min Act: -0.0000

Data Index: 544525 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2743. Min Act: -0.0000

Data Index: 932569 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1797388 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2939. Min Act: -0.0000

Data Index: 400655 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2799. Min Act: -0.0000

Data Index: 1745468 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1277343 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1666995 (The Pile)

Max Activating Token Index: 98

Text #15

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2697. Min Act: -0.0000

Data Index: 149276 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1930698 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1923549 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2754. Min Act: -0.0000

Data Index: 744930 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1435928 (The Pile)

Max Activating Token Index: 157