Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4234 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1631217 (Python Code)

Max Activating Token Index: 980

Text #1

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0984. Min Act: -0.0000

Data Index: 1429058 (Python Code)

Max Activating Token Index: 182

Text #2

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1468503 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1450554 (Python Code)

Max Activating Token Index: 851

Text #4

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1539307 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1361247 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1442233 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1421302 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1575743 (Python Code)

Max Activating Token Index: 115

Text #9

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1382387 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1575398 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1621068 (Python Code)

Max Activating Token Index: 206

Text #12

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9691. Min Act: 0.0000

Data Index: 1494775 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1606035 (Python Code)

Max Activating Token Index: 953

Text #14

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1593320 (Python Code)

Max Activating Token Index: 802

Text #15

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1360764 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1545958 (Python Code)

Max Activating Token Index: 391

Text #17

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1452963 (Python Code)

Max Activating Token Index: 245

Text #18

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1592566 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.8751. Min Act: -0.0000

Data Index: 1452466 (Python Code)

Max Activating Token Index: 105