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

Dataset: The Pile

Neuron 4583 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: 0.8855. Min Range: -0.8855

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1839041 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.8676. Min Act: -0.0000

Data Index: 386486 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7480. Min Act: -0.0000

Data Index: 724083 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.8136. Min Act: -0.0000

Data Index: 672095 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1046703 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7523. Min Act: -0.0000

Data Index: 705525 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1800147 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7628. Min Act: -0.0000

Data Index: 216515 (The Pile)

Max Activating Token Index: 39

Text #8

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.6741. Min Act: -0.0000

Data Index: 974650 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7309. Min Act: -0.0000

Data Index: 353898 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1357027 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7142. Min Act: -0.0000

Data Index: 604381 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7206. Min Act: -0.0000

Data Index: 988835 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1111996 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1036337 (The Pile)

Max Activating Token Index: 26

Text #15

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1410917 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7739. Min Act: -0.0000

Data Index: 724266 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1830215 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1335688 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.6672. Min Act: -0.0000

Data Index: 733771 (The Pile)

Max Activating Token Index: 64