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

Dataset: The Pile

Neuron 282 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: 0.3854. Min Range: -0.3854

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1186855 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1586178 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3545. Min Act: -0.0000

Data Index: 476265 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3531. Min Act: -0.0000

Data Index: 766921 (The Pile)

Max Activating Token Index: 989

Text #4

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3112. Min Act: -0.0000

Data Index: 701657 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3329. Min Act: -0.0000

Data Index: 305533 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1447350 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1327086 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1014177 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1497341 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2850. Min Act: -0.0000

Data Index: 492235 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1207389 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1147958 (The Pile)

Max Activating Token Index: 652

Text #13

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.3052. Min Act: -0.0000

Data Index: 727708 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2791. Min Act: -0.0000

Data Index: 89963 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1625549 (The Pile)

Max Activating Token Index: 220

Text #16

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2733. Min Act: -0.0000

Data Index: 823126 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1109657 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2463. Min Act: -0.0000

Data Index: 275866 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 0.3854. Min Range: -0.3854

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1468078 (The Pile)

Max Activating Token Index: 515