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

Dataset: The Pile

Neuron 3294 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.4179. Min Act: -0.0000

Data Index: 250901 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1443517 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1928845 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1400647 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.8404. Min Act: -0.0000

Data Index: 319100 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.7860. Min Act: -0.0000

Data Index: 905358 (The Pile)

Max Activating Token Index: 463

Text #6

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1839385 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1945265 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1690258 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.6667. Min Act: -0.0000

Data Index: 457041 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.6912. Min Act: -0.0000

Data Index: 14570 (The Pile)

Max Activating Token Index: 659

Text #11

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1988430 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1897791 (The Pile)

Max Activating Token Index: 529

Text #13

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1674067 (The Pile)

Max Activating Token Index: 616

Text #14

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.6595. Min Act: -0.0000

Data Index: 224522 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1029320 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1424861 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.6848. Min Act: -0.0000

Data Index: 500896 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.7225. Min Act: -0.0000

Data Index: 1003687 (The Pile)

Max Activating Token Index: 619

Text #19

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.7400. Min Act: -0.0000

Data Index: 718114 (The Pile)

Max Activating Token Index: 137