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

Dataset: The Pile

Neuron 3529 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9575. Min Range: -5.9575

Max Act: 5.9575. Min Act: -0.0000

Data Index: 1568192 (The Pile)

Max Activating Token Index: 354

Text #1

Max Range: 5.9575. Min Range: -5.9575

Max Act: 5.4010. Min Act: -0.0000

Data Index: 625680 (The Pile)

Max Activating Token Index: 342

Text #2

Max Range: 5.9575. Min Range: -5.9575

Max Act: 5.0177. Min Act: -0.0000

Data Index: 915661 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 5.9575. Min Range: -5.9575

Max Act: 3.9085. Min Act: -0.0000

Data Index: 1067862 (The Pile)

Max Activating Token Index: 741

Text #4

Max Range: 5.9575. Min Range: -5.9575

Max Act: 4.0574. Min Act: -0.0000

Data Index: 1000677 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 5.9575. Min Range: -5.9575

Max Act: 3.4134. Min Act: -0.0000

Data Index: 1001011 (The Pile)

Max Activating Token Index: 367

Text #6

Max Range: 5.9575. Min Range: -5.9575

Max Act: 3.1686. Min Act: -0.0000

Data Index: 1555886 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 5.9575. Min Range: -5.9575

Max Act: 3.1632. Min Act: -0.0000

Data Index: 115343 (The Pile)

Max Activating Token Index: 737

Text #8

Max Range: 5.9575. Min Range: -5.9575

Max Act: 3.0927. Min Act: -0.0000

Data Index: 1914238 (The Pile)

Max Activating Token Index: 399

Text #9

Max Range: 5.9575. Min Range: -5.9575

Max Act: 3.0672. Min Act: -0.0000

Data Index: 119879 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 5.9575. Min Range: -5.9575

Max Act: 3.1781. Min Act: -0.0000

Data Index: 1259751 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 5.9575. Min Range: -5.9575

Max Act: 2.7088. Min Act: -0.0000

Data Index: 244971 (The Pile)

Max Activating Token Index: 904

Text #12

Max Range: 5.9575. Min Range: -5.9575

Max Act: 2.9710. Min Act: -0.0000

Data Index: 1894305 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 5.9575. Min Range: -5.9575

Max Act: 2.9932. Min Act: -0.0000

Data Index: 278770 (The Pile)

Max Activating Token Index: 729

Text #14

Max Range: 5.9575. Min Range: -5.9575

Max Act: 2.9667. Min Act: -0.0000

Data Index: 1836866 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 5.9575. Min Range: -5.9575

Max Act: 2.9501. Min Act: -0.0000

Data Index: 1600188 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 5.9575. Min Range: -5.9575

Max Act: 3.0391. Min Act: -0.0000

Data Index: 681298 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 5.9575. Min Range: -5.9575

Max Act: 2.8681. Min Act: -0.0000

Data Index: 825928 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 5.9575. Min Range: -5.9575

Max Act: 2.8346. Min Act: 0.0000

Data Index: 896475 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 5.9575. Min Range: -5.9575

Max Act: 2.6687. Min Act: -0.0000

Data Index: 1677648 (The Pile)

Max Activating Token Index: 529