Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 653 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3926. Min Range: -4.3926

Max Act: 4.0640. Min Act: -0.0000

Data Index: 197811 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 4.3926. Min Range: -4.3926

Max Act: 4.3926. Min Act: -0.0000

Data Index: 123097 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 4.3926. Min Range: -4.3926

Max Act: 4.0365. Min Act: -0.0000

Data Index: 1108145 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 4.3926. Min Range: -4.3926

Max Act: 4.0618. Min Act: -0.0000

Data Index: 773945 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.5546. Min Act: -0.0000

Data Index: 959721 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.4844. Min Act: -0.0000

Data Index: 119313 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.6258. Min Act: -0.0000

Data Index: 231980 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.1233. Min Act: -0.0000

Data Index: 1056743 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.3591. Min Act: -0.0000

Data Index: 491409 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.2939. Min Act: -0.0000

Data Index: 849020 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.5803. Min Act: -0.0000

Data Index: 147507 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.2087. Min Act: -0.0000

Data Index: 447749 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.1639. Min Act: -0.0000

Data Index: 689862 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.1477. Min Act: -0.0000

Data Index: 54841 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.1134. Min Act: -0.0000

Data Index: 1067862 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 4.3926. Min Range: -4.3926

Max Act: 2.9569. Min Act: -0.0000

Data Index: 1054911 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.0874. Min Act: -0.0000

Data Index: 1278388 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 4.3926. Min Range: -4.3926

Max Act: 2.8934. Min Act: -0.0000

Data Index: 438767 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 4.3926. Min Range: -4.3926

Max Act: 2.8909. Min Act: -0.0000

Data Index: 430918 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 4.3926. Min Range: -4.3926

Max Act: 3.0233. Min Act: -0.0000

Data Index: 704016 (C4 (Web Text))

Max Activating Token Index: 487