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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4392 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.2404. Min Act: -0.0000

Data Index: 371829 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.2945. Min Act: -0.0000

Data Index: 321223 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1078. Min Act: -0.0000

Data Index: 637201 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0918. Min Act: -0.0001

Data Index: 544964 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1551. Min Act: -0.0000

Data Index: 299245 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0466. Min Act: -0.0000

Data Index: 672415 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0143. Min Act: -0.0001

Data Index: 1135946 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0344. Min Act: -0.0001

Data Index: 1066757 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.8633. Min Act: -0.0000

Data Index: 82667 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9585. Min Act: -0.0000

Data Index: 825307 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.8137. Min Act: -0.0000

Data Index: 59818 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9183. Min Act: -0.0001

Data Index: 942367 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.8571. Min Act: -0.0000

Data Index: 975910 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9017. Min Act: -0.0000

Data Index: 376097 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9448. Min Act: -0.0001

Data Index: 119470 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9339. Min Act: -0.0001

Data Index: 748980 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.8323. Min Act: -0.0000

Data Index: 127855 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.8739. Min Act: -0.0001

Data Index: 511103 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9596. Min Act: -0.0000

Data Index: 628804 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.8807. Min Act: -0.0000

Data Index: 412697 (C4 (Web Text))

Max Activating Token Index: 11