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

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

Neuron 1277 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.4833. Min Act: -0.0000

Data Index: 1599584 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1369335 (Python Code)

Max Activating Token Index: 76

Text #2

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1440526 (Python Code)

Max Activating Token Index: 173

Text #3

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1526352 (Python Code)

Max Activating Token Index: 740

Text #4

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.0908. Min Act: -0.0000

Data Index: 521067 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.0953. Min Act: -0.0000

Data Index: 82872 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1424323 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1303162 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1629132 (Python Code)

Max Activating Token Index: 84

Text #9

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.0184. Min Act: -0.0000

Data Index: 1643125 (Python Code)

Max Activating Token Index: 913

Text #10

Max Range: 1.4833. Min Range: -1.4833

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1424272 (Python Code)

Max Activating Token Index: 902

Text #11

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1603804 (Python Code)

Max Activating Token Index: 312

Text #12

Max Range: 1.4833. Min Range: -1.4833

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1583193 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.0048. Min Act: -0.0000

Data Index: 643987 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.4833. Min Range: -1.4833

Max Act: 0.9503. Min Act: -0.0000

Data Index: 1601198 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 1.4833. Min Range: -1.4833

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1588799 (Python Code)

Max Activating Token Index: 774

Text #16

Max Range: 1.4833. Min Range: -1.4833

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1239536 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 1.4833. Min Range: -1.4833

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1460943 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 1.4833. Min Range: -1.4833

Max Act: 0.9286. Min Act: -0.0000

Data Index: 349567 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.4833. Min Range: -1.4833

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1596957 (Python Code)

Max Activating Token Index: 757