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

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

Neuron 521 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0026. Min Range: -1.0026

Max Act: 1.0022. Min Act: -0.0001

Data Index: 1506978 (Python Code)

Max Activating Token Index: 660

Text #1

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9834. Min Act: -0.0001

Data Index: 1514854 (Python Code)

Max Activating Token Index: 509

Text #2

Max Range: 1.0026. Min Range: -1.0026

Max Act: 1.0026. Min Act: -0.0001

Data Index: 1622931 (Python Code)

Max Activating Token Index: 404

Text #3

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9688. Min Act: -0.0001

Data Index: 1427170 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9154. Min Act: -0.0001

Data Index: 1493644 (Python Code)

Max Activating Token Index: 618

Text #5

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9394. Min Act: -0.0001

Data Index: 1362421 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9295. Min Act: -0.0002

Data Index: 1604947 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9305. Min Act: -0.0001

Data Index: 1419607 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8966. Min Act: -0.0001

Data Index: 1528909 (Python Code)

Max Activating Token Index: 325

Text #9

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9556. Min Act: -0.0001

Data Index: 1527769 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9343. Min Act: -0.0001

Data Index: 1517001 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9338. Min Act: -0.0001

Data Index: 1634809 (Python Code)

Max Activating Token Index: 681

Text #12

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9539. Min Act: -0.0001

Data Index: 1645050 (Python Code)

Max Activating Token Index: 526

Text #13

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8698. Min Act: -0.0001

Data Index: 1373020 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9005. Min Act: -0.0001

Data Index: 1520876 (Python Code)

Max Activating Token Index: 912

Text #15

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9125. Min Act: -0.0001

Data Index: 1469352 (Python Code)

Max Activating Token Index: 653

Text #16

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8617. Min Act: -0.0001

Data Index: 1580224 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8945. Min Act: -0.0001

Data Index: 1473844 (Python Code)

Max Activating Token Index: 862

Text #18

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8034. Min Act: -0.0001

Data Index: 1535874 (Python Code)

Max Activating Token Index: 320

Text #19

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9335. Min Act: -0.0001

Data Index: 1638298 (Python Code)

Max Activating Token Index: 611