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

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

Neuron 92 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: 2.0519. Min Range: -2.0519

Max Act: 1.9604. Min Act: -0.0000

Data Index: 1420242 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 2.0519. Min Range: -2.0519

Max Act: 2.0519. Min Act: -0.0000

Data Index: 1567865 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.8088. Min Act: -0.0000

Data Index: 1637268 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.8109. Min Act: -0.0000

Data Index: 1529600 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.7903. Min Act: -0.0000

Data Index: 1629571 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.8541. Min Act: -0.0000

Data Index: 1435359 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1468387 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.6416. Min Act: -0.0000

Data Index: 1561116 (Python Code)

Max Activating Token Index: 740

Text #8

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.5895. Min Act: -0.0000

Data Index: 1472451 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1419010 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.5871. Min Act: -0.0000

Data Index: 1558279 (Python Code)

Max Activating Token Index: 27

Text #11

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.5814. Min Act: -0.0000

Data Index: 1609311 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.5643. Min Act: -0.0000

Data Index: 1459235 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.5416. Min Act: -0.0000

Data Index: 1568578 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1575775 (Python Code)

Max Activating Token Index: 499

Text #15

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.4398. Min Act: -0.0000

Data Index: 1383877 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1581375 (Python Code)

Max Activating Token Index: 76

Text #17

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1653700 (Python Code)

Max Activating Token Index: 243

Text #18

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.5821. Min Act: -0.0000

Data Index: 1588347 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 2.0519. Min Range: -2.0519

Max Act: 1.4489. Min Act: -0.0000

Data Index: 1529553 (Python Code)

Max Activating Token Index: 28