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

Dataset: The Pile

Neuron 270 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.8418. Min Act: -0.0000

Data Index: 1653712 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.6047. Min Act: -0.0000

Data Index: 918648 (The Pile)

Max Activating Token Index: 268

Text #2

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.4155. Min Act: -0.0000

Data Index: 234406 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.5907. Min Act: -0.0000

Data Index: 1842220 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.4812. Min Act: -0.0000

Data Index: 119202 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.3006. Min Act: 0.0000

Data Index: 803633 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 3.8418. Min Range: -3.8418

Max Act: 2.9510. Min Act: -0.0000

Data Index: 403476 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 3.8418. Min Range: -3.8418

Max Act: 2.9239. Min Act: -0.0000

Data Index: 1054958 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.0182. Min Act: -0.0000

Data Index: 1253909 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.3975. Min Act: -0.0000

Data Index: 1103701 (The Pile)

Max Activating Token Index: 69

Text #10

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.2499. Min Act: -0.0000

Data Index: 1691199 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.2511. Min Act: -0.0000

Data Index: 89532 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.0456. Min Act: -0.0000

Data Index: 1336760 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 3.8418. Min Range: -3.8418

Max Act: 2.8585. Min Act: -0.0000

Data Index: 367975 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.1301. Min Act: -0.0000

Data Index: 1519090 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.0790. Min Act: -0.0000

Data Index: 1887060 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 3.8418. Min Range: -3.8418

Max Act: 2.9194. Min Act: -0.0000

Data Index: 1141920 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 3.8418. Min Range: -3.8418

Max Act: 2.9187. Min Act: -0.0000

Data Index: 467852 (The Pile)

Max Activating Token Index: 531

Text #18

Max Range: 3.8418. Min Range: -3.8418

Max Act: 3.0685. Min Act: -0.0000

Data Index: 1560946 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 3.8418. Min Range: -3.8418

Max Act: 2.9139. Min Act: -0.0000

Data Index: 653837 (The Pile)

Max Activating Token Index: 47