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

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

Neuron 2773 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1424. Min Range: -1.1424

Max Act: 1.1424. Min Act: -0.0000

Data Index: 795554 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.1424. Min Range: -1.1424

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1291994 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.9552. Min Act: -0.0000

Data Index: 225976 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1178861 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8922. Min Act: -0.0000

Data Index: 565941 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.9092. Min Act: -0.0000

Data Index: 950391 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1286346 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.9841. Min Act: -0.0000

Data Index: 630169 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8827. Min Act: -0.0000

Data Index: 697177 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1265979 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1320481 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1353303 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8057. Min Act: -0.0000

Data Index: 625927 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1306840 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7784. Min Act: -0.0000

Data Index: 513897 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7955. Min Act: -0.0000

Data Index: 467571 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7572. Min Act: -0.0000

Data Index: 820727 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7615. Min Act: -0.0000

Data Index: 339778 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1226531 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7733. Min Act: -0.0000

Data Index: 17973 (C4 (Web Text))

Max Activating Token Index: 743