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

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

Neuron 4187 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0790. Min Range: -2.0790

Max Act: 2.0790. Min Act: -0.0000

Data Index: 1644115 (Python Code)

Max Activating Token Index: 884

Text #1

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.9441. Min Act: -0.0000

Data Index: 1410903 (Python Code)

Max Activating Token Index: 187

Text #2

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.6757. Min Act: -0.0000

Data Index: 1612010 (Python Code)

Max Activating Token Index: 793

Text #3

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.7888. Min Act: -0.0000

Data Index: 1534037 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.6756. Min Act: -0.0000

Data Index: 1533455 (Python Code)

Max Activating Token Index: 262

Text #5

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.7601. Min Act: -0.0000

Data Index: 1395218 (Python Code)

Max Activating Token Index: 526

Text #6

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1458772 (Python Code)

Max Activating Token Index: 954

Text #7

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.7544. Min Act: -0.0000

Data Index: 1528347 (Python Code)

Max Activating Token Index: 692

Text #8

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.6960. Min Act: -0.0000

Data Index: 1380227 (Python Code)

Max Activating Token Index: 345

Text #9

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.6463. Min Act: -0.0000

Data Index: 1492559 (Python Code)

Max Activating Token Index: 228

Text #10

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.6736. Min Act: -0.0000

Data Index: 1484167 (Python Code)

Max Activating Token Index: 596

Text #11

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.7422. Min Act: -0.0000

Data Index: 1624627 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.6357. Min Act: -0.0000

Data Index: 1541636 (Python Code)

Max Activating Token Index: 763

Text #13

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.6479. Min Act: -0.0000

Data Index: 1528049 (Python Code)

Max Activating Token Index: 952

Text #14

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1385748 (Python Code)

Max Activating Token Index: 680

Text #15

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.6161. Min Act: -0.0000

Data Index: 1491914 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.5054. Min Act: -0.0000

Data Index: 1589711 (Python Code)

Max Activating Token Index: 397

Text #17

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.5847. Min Act: -0.0000

Data Index: 1628718 (Python Code)

Max Activating Token Index: 167

Text #18

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.5818. Min Act: -0.0000

Data Index: 1436420 (Python Code)

Max Activating Token Index: 586

Text #19

Max Range: 2.0790. Min Range: -2.0790

Max Act: 1.4996. Min Act: -0.0000

Data Index: 1546863 (Python Code)

Max Activating Token Index: 744