Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1027 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2600. Min Act: -0.0000

Data Index: 274663 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1346903 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2266. Min Act: -0.0000

Data Index: 147071 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1236479 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1115124 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1802. Min Act: -0.0000

Data Index: 906054 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1791. Min Act: -0.0000

Data Index: 476655 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1043502 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1610. Min Act: -0.0000

Data Index: 865845 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1852. Min Act: -0.0000

Data Index: 971812 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1262631 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1641. Min Act: -0.0000

Data Index: 603890 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1569. Min Act: -0.0000

Data Index: 824091 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1238711 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1673. Min Act: -0.0000

Data Index: 776040 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1250227 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1706. Min Act: -0.0000

Data Index: 897794 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1777. Min Act: -0.0000

Data Index: 137936 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1197922 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1583. Min Act: -0.0000

Data Index: 121107 (C4 (Web Text))

Max Activating Token Index: 456