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

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

Neuron 2845 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1633858 (Python Code)

Max Activating Token Index: 94

Text #1

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.5820. Min Act: -0.0000

Data Index: 878205 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1651411 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1528917 (Python Code)

Max Activating Token Index: 275

Text #4

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1416583 (Python Code)

Max Activating Token Index: 697

Text #5

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1389973 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1648581 (Python Code)

Max Activating Token Index: 698

Text #7

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1617135 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1556476 (Python Code)

Max Activating Token Index: 215

Text #9

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1388311 (Python Code)

Max Activating Token Index: 87

Text #10

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1450743 (Python Code)

Max Activating Token Index: 661

Text #11

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.5208. Min Act: -0.0000

Data Index: 828893 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1621030 (Python Code)

Max Activating Token Index: 172

Text #13

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1484799 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1499860 (Python Code)

Max Activating Token Index: 259

Text #15

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1412449 (Python Code)

Max Activating Token Index: 988

Text #16

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1445521 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1543444 (Python Code)

Max Activating Token Index: 907

Text #18

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1615758 (Python Code)

Max Activating Token Index: 245

Text #19

Max Range: 0.8378. Min Range: -0.8378

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1600507 (Python Code)

Max Activating Token Index: 179