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

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

Neuron 3679 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.6615. Min Act: -0.0000

Data Index: 388851 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.5343. Min Act: -0.0000

Data Index: 389323 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.4053. Min Act: -0.0000

Data Index: 497392 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.1814. Min Act: -0.0000

Data Index: 768657 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.3964. Min Act: -0.0000

Data Index: 199052 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.1868. Min Act: -0.0000

Data Index: 668108 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.1838. Min Act: -0.0000

Data Index: 166393 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.0753. Min Act: -0.0000

Data Index: 573282 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.2846. Min Act: -0.0000

Data Index: 1309866 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 2.6615. Min Range: -2.6615

Max Act: 1.9922. Min Act: -0.0000

Data Index: 189626 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 2.6615. Min Range: -2.6615

Max Act: 1.9826. Min Act: -0.0000

Data Index: 321838 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 2.6615. Min Range: -2.6615

Max Act: 1.9805. Min Act: -0.0000

Data Index: 1120578 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.1028. Min Act: -0.0000

Data Index: 212102 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.0689. Min Act: -0.0000

Data Index: 636315 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.0737. Min Act: -0.0000

Data Index: 260308 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.0568. Min Act: -0.0000

Data Index: 125918 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.0154. Min Act: -0.0000

Data Index: 310342 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.0018. Min Act: -0.0000

Data Index: 799015 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 2.6615. Min Range: -2.6615

Max Act: 2.1120. Min Act: -0.0000

Data Index: 188356 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 2.6615. Min Range: -2.6615

Max Act: 1.9870. Min Act: -0.0000

Data Index: 298189 (C4 (Web Text))

Max Activating Token Index: 1018