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

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

Neuron 3894 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8327. Min Act: -0.0000

Data Index: 406619 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8682. Min Act: -0.0000

Data Index: 688182 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5784. Min Act: -0.0000

Data Index: 663332 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7388. Min Act: -0.0001

Data Index: 1328662 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.9035. Min Act: -0.0000

Data Index: 1065067 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8709. Min Act: -0.0000

Data Index: 138276 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8164. Min Act: -0.0000

Data Index: 716723 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1133909 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7772. Min Act: -0.0000

Data Index: 248280 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7438. Min Act: -0.0001

Data Index: 420322 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1162993 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6410. Min Act: -0.0000

Data Index: 457241 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6430. Min Act: -0.0000

Data Index: 125803 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6910. Min Act: -0.0000

Data Index: 848325 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.7119. Min Act: -0.0000

Data Index: 932227 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6937. Min Act: -0.0001

Data Index: 951652 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1015547 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6469. Min Act: -0.0001

Data Index: 496532 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1243137 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6963. Min Act: -0.0000

Data Index: 308883 (C4 (Web Text))

Max Activating Token Index: 619