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

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

Neuron 987 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1651763 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1557897 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1551983 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1471437 (Python Code)

Max Activating Token Index: 1000

Text #4

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1385444 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1531177 (Python Code)

Max Activating Token Index: 293

Text #6

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1400358 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1651629 (Python Code)

Max Activating Token Index: 396

Text #8

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1510306 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1643886 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1557986 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1487172 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1494639 (Python Code)

Max Activating Token Index: 90

Text #13

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1420421 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1541695 (Python Code)

Max Activating Token Index: 212

Text #15

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1590046 (Python Code)

Max Activating Token Index: 829

Text #16

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1535161 (Python Code)

Max Activating Token Index: 287

Text #17

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1540201 (Python Code)

Max Activating Token Index: 167

Text #18

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1546771 (Python Code)

Max Activating Token Index: 612

Text #19

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1447117 (Python Code)

Max Activating Token Index: 112