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

Dataset: The Pile

Neuron 3334 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.8401. Min Act: -0.0000

Data Index: 361851 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1896737 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.7077. Min Act: -0.0000

Data Index: 701115 (The Pile)

Max Activating Token Index: 518

Text #3

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1314306 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.7014. Min Act: -0.0000

Data Index: 236016 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6717. Min Act: -0.0000

Data Index: 59907 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1801936 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1574328 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6090. Min Act: -0.0000

Data Index: 510615 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1461080 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1914198 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1375473 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1009705 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5612. Min Act: -0.0000

Data Index: 982664 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5360. Min Act: -0.0000

Data Index: 92851 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5500. Min Act: -0.0000

Data Index: 852896 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1170335 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1108023 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1348727 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1119090 (The Pile)

Max Activating Token Index: 314