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

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

Neuron 4700 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1427721 (Python Code)

Max Activating Token Index: 623

Text #1

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.6801. Min Act: 0.0001

Data Index: 1494691 (Python Code)

Max Activating Token Index: 626

Text #2

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1392431 (Python Code)

Max Activating Token Index: 651

Text #3

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.6525. Min Act: 0.0001

Data Index: 1647070 (Python Code)

Max Activating Token Index: 247

Text #4

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1485743 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5514. Min Act: 0.0002

Data Index: 1392879 (Python Code)

Max Activating Token Index: 534

Text #6

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1422152 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1606552 (Python Code)

Max Activating Token Index: 302

Text #8

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1373167 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1443796 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1604587 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5135. Min Act: 0.0001

Data Index: 1632351 (Python Code)

Max Activating Token Index: 973

Text #12

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1498636 (Python Code)

Max Activating Token Index: 249

Text #13

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4931. Min Act: 0.0000

Data Index: 1613083 (Python Code)

Max Activating Token Index: 868

Text #14

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1631861 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5006. Min Act: 0.0000

Data Index: 1571183 (Python Code)

Max Activating Token Index: 767

Text #16

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4901. Min Act: 0.0003

Data Index: 1514176 (Python Code)

Max Activating Token Index: 966

Text #17

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4771. Min Act: 0.0000

Data Index: 1405980 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4882. Min Act: 0.0001

Data Index: 1404243 (Python Code)

Max Activating Token Index: 465

Text #19

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1518574 (Python Code)

Max Activating Token Index: 680