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

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

Neuron 5132 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3521. Min Range: -2.3521

Max Act: 2.3521. Min Act: -0.0000

Data Index: 411072 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.8596. Min Act: -0.0000

Data Index: 495006 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.9583. Min Act: -0.0000

Data Index: 576656 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.9163. Min Act: -0.0000

Data Index: 943862 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.8697. Min Act: -0.0000

Data Index: 944147 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.7516. Min Act: -0.0000

Data Index: 29339 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.7072. Min Act: -0.0000

Data Index: 1068355 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.5269. Min Act: -0.0000

Data Index: 508046 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.7698. Min Act: -0.0000

Data Index: 569194 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.6975. Min Act: -0.0000

Data Index: 920055 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.7644. Min Act: -0.0000

Data Index: 885388 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.7373. Min Act: -0.0000

Data Index: 697775 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.6538. Min Act: -0.0000

Data Index: 996575 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.7325. Min Act: -0.0000

Data Index: 574768 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.6260. Min Act: -0.0000

Data Index: 1079126 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.6301. Min Act: -0.0000

Data Index: 1004793 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.6156. Min Act: -0.0000

Data Index: 1065620 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.6227. Min Act: -0.0000

Data Index: 1211673 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.7072. Min Act: -0.0000

Data Index: 949177 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 2.3521. Min Range: -2.3521

Max Act: 1.7133. Min Act: -0.0000

Data Index: 29083 (C4 (Web Text))

Max Activating Token Index: 156