Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1491 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.4194. Min Act: -0.0001

Data Index: 1591878 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2069. Min Act: -0.0001

Data Index: 1585149 (Python Code)

Max Activating Token Index: 946

Text #2

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.1783. Min Act: -0.0001

Data Index: 1452575 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0837. Min Act: -0.0001

Data Index: 1500554 (Python Code)

Max Activating Token Index: 53

Text #4

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0207. Min Act: -0.0001

Data Index: 1546930 (Python Code)

Max Activating Token Index: 368

Text #5

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1607241 (Python Code)

Max Activating Token Index: 462

Text #6

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1526884 (Python Code)

Max Activating Token Index: 867

Text #7

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1654008 (Python Code)

Max Activating Token Index: 255

Text #8

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0168. Min Act: -0.0001

Data Index: 1513917 (Python Code)

Max Activating Token Index: 825

Text #9

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1620865 (Python Code)

Max Activating Token Index: 203

Text #10

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1617598 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9548. Min Act: -0.0001

Data Index: 1556643 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9157. Min Act: -0.0001

Data Index: 1435480 (Python Code)

Max Activating Token Index: 130

Text #13

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9492. Min Act: -0.0001

Data Index: 1392726 (Python Code)

Max Activating Token Index: 298

Text #14

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1634872 (Python Code)

Max Activating Token Index: 372

Text #15

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.8892. Min Act: -0.0001

Data Index: 1641550 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.8529. Min Act: -0.0001

Data Index: 1630592 (Python Code)

Max Activating Token Index: 606

Text #17

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.8444. Min Act: -0.0001

Data Index: 1590171 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1634433 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.8659. Min Act: -0.0001

Data Index: 1435625 (Python Code)

Max Activating Token Index: 195