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

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

Neuron 2154 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: 1.2215. Min Range: -1.2215

Max Act: 1.0887. Min Act: -0.0000

Data Index: 1537343 (Python Code)

Max Activating Token Index: 281

Text #1

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.2215. Min Act: -0.0000

Data Index: 1401047 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1599061 (Python Code)

Max Activating Token Index: 452

Text #3

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1392. Min Act: -0.0000

Data Index: 1477850 (Python Code)

Max Activating Token Index: 584

Text #4

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1451879 (Python Code)

Max Activating Token Index: 397

Text #5

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1618312 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1388. Min Act: -0.0000

Data Index: 1416041 (Python Code)

Max Activating Token Index: 883

Text #7

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1098. Min Act: -0.0000

Data Index: 1609200 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1079. Min Act: -0.0000

Data Index: 1492122 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1421681 (Python Code)

Max Activating Token Index: 646

Text #10

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.0732. Min Act: -0.0000

Data Index: 1639901 (Python Code)

Max Activating Token Index: 900

Text #11

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.0973. Min Act: -0.0000

Data Index: 1466760 (Python Code)

Max Activating Token Index: 261

Text #12

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.0998. Min Act: -0.0000

Data Index: 1489008 (Python Code)

Max Activating Token Index: 352

Text #13

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1491850 (Python Code)

Max Activating Token Index: 424

Text #14

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1325. Min Act: -0.0000

Data Index: 1656260 (Python Code)

Max Activating Token Index: 468

Text #15

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1478467 (Python Code)

Max Activating Token Index: 519

Text #16

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1626261 (Python Code)

Max Activating Token Index: 455

Text #17

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1595586 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1581064 (Python Code)

Max Activating Token Index: 340

Text #19

Max Range: 1.2215. Min Range: -1.2215

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1568873 (Python Code)

Max Activating Token Index: 822