Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2786 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.2883. Min Act: -0.0001

Data Index: 1401148 (Python Code)

Max Activating Token Index: 558

Text #1

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.3088. Min Act: -0.0001

Data Index: 1559187 (Python Code)

Max Activating Token Index: 533

Text #2

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.2992. Min Act: -0.0001

Data Index: 1456792 (Python Code)

Max Activating Token Index: 904

Text #3

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.1063. Min Act: -0.0001

Data Index: 1455484 (Python Code)

Max Activating Token Index: 541

Text #4

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.2546. Min Act: -0.0001

Data Index: 1656302 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.2323. Min Act: -0.0001

Data Index: 1598091 (Python Code)

Max Activating Token Index: 664

Text #6

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0920. Min Act: -0.0001

Data Index: 1520159 (Python Code)

Max Activating Token Index: 943

Text #7

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0879. Min Act: -0.0001

Data Index: 1565337 (Python Code)

Max Activating Token Index: 329

Text #8

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9981. Min Act: -0.0001

Data Index: 1550594 (Python Code)

Max Activating Token Index: 627

Text #9

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9564. Min Act: -0.0001

Data Index: 1547154 (Python Code)

Max Activating Token Index: 664

Text #10

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0139. Min Act: -0.0001

Data Index: 1646143 (Python Code)

Max Activating Token Index: 882

Text #11

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0114. Min Act: -0.0001

Data Index: 1586672 (Python Code)

Max Activating Token Index: 203

Text #12

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.8977. Min Act: -0.0001

Data Index: 1548733 (Python Code)

Max Activating Token Index: 832

Text #13

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0245. Min Act: -0.0001

Data Index: 1489343 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9281. Min Act: -0.0001

Data Index: 1511714 (Python Code)

Max Activating Token Index: 767

Text #15

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9885. Min Act: -0.0001

Data Index: 1588564 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9864. Min Act: -0.0001

Data Index: 1548334 (Python Code)

Max Activating Token Index: 118

Text #17

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9517. Min Act: -0.0001

Data Index: 1457931 (Python Code)

Max Activating Token Index: 228

Text #18

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9748. Min Act: -0.0001

Data Index: 1636506 (Python Code)

Max Activating Token Index: 821

Text #19

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9524. Min Act: -0.0001

Data Index: 1556597 (Python Code)

Max Activating Token Index: 205