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

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

Neuron 4946 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0852. Min Range: -1.0852

Max Act: 1.0852. Min Act: -0.0001

Data Index: 1390859 (Python Code)

Max Activating Token Index: 784

Text #1

Max Range: 1.0852. Min Range: -1.0852

Max Act: 1.0221. Min Act: -0.0001

Data Index: 1565953 (Python Code)

Max Activating Token Index: 60

Text #2

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8867. Min Act: -0.0001

Data Index: 1650293 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8548. Min Act: -0.0001

Data Index: 1585185 (Python Code)

Max Activating Token Index: 335

Text #4

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8527. Min Act: -0.0001

Data Index: 1560223 (Python Code)

Max Activating Token Index: 160

Text #5

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8006. Min Act: -0.0001

Data Index: 1490591 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8017. Min Act: -0.0001

Data Index: 884748 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7740. Min Act: -0.0001

Data Index: 1415407 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7798. Min Act: -0.0001

Data Index: 1383618 (Python Code)

Max Activating Token Index: 630

Text #9

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7784. Min Act: -0.0001

Data Index: 1633242 (Python Code)

Max Activating Token Index: 330

Text #10

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8028. Min Act: -0.0001

Data Index: 1549608 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8199. Min Act: -0.0001

Data Index: 1487734 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1370301 (Python Code)

Max Activating Token Index: 652

Text #13

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7381. Min Act: -0.0001

Data Index: 1634987 (Python Code)

Max Activating Token Index: 857

Text #14

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7191. Min Act: -0.0001

Data Index: 1516604 (Python Code)

Max Activating Token Index: 505

Text #15

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7082. Min Act: -0.0001

Data Index: 1430488 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.6840. Min Act: -0.0001

Data Index: 1413441 (Python Code)

Max Activating Token Index: 718

Text #17

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7358. Min Act: -0.0001

Data Index: 1372439 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7204. Min Act: -0.0001

Data Index: 1630712 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7164. Min Act: -0.0001

Data Index: 1597332 (Python Code)

Max Activating Token Index: 938