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

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

Neuron 4598 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1995. Min Act: -0.0002

Data Index: 379115 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.2019. Min Act: -0.0002

Data Index: 182792 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1867. Min Act: -0.0002

Data Index: 671488 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.2168. Min Act: -0.0002

Data Index: 273430 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.2101. Min Act: -0.0002

Data Index: 1175571 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.2041. Min Act: -0.0002

Data Index: 1055608 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1958. Min Act: -0.0002

Data Index: 444242 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1904. Min Act: -0.0002

Data Index: 576884 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1988. Min Act: -0.0002

Data Index: 242514 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1973. Min Act: -0.0002

Data Index: 1196523 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1869. Min Act: -0.0002

Data Index: 1021081 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1724. Min Act: -0.0002

Data Index: 532930 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.2020. Min Act: -0.0002

Data Index: 950410 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1727. Min Act: -0.0002

Data Index: 1348021 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1902. Min Act: -0.0002

Data Index: 673054 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1764. Min Act: -0.0002

Data Index: 314693 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1728. Min Act: -0.0002

Data Index: 1306756 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1972. Min Act: -0.0002

Data Index: 1215092 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1817. Min Act: -0.0002

Data Index: 982794 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1657. Min Act: -0.0002

Data Index: 70237 (C4 (Web Text))

Max Activating Token Index: 229