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

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

Neuron 407 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: 2.1032. Min Range: -2.1032

Max Act: 2.1032. Min Act: -0.0000

Data Index: 285363 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 2.1032. Min Range: -2.1032

Max Act: 2.0737. Min Act: -0.0000

Data Index: 1361494 (Python Code)

Max Activating Token Index: 739

Text #2

Max Range: 2.1032. Min Range: -2.1032

Max Act: 2.0239. Min Act: -0.0000

Data Index: 1168645 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 2.1032. Min Range: -2.1032

Max Act: 2.0241. Min Act: -0.0000

Data Index: 481614 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.8412. Min Act: -0.0000

Data Index: 1150795 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.9893. Min Act: -0.0000

Data Index: 706312 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.9768. Min Act: -0.0000

Data Index: 1620322 (Python Code)

Max Activating Token Index: 681

Text #7

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.8720. Min Act: -0.0000

Data Index: 1575241 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.8989. Min Act: -0.0000

Data Index: 881061 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.9300. Min Act: -0.0000

Data Index: 337968 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.7595. Min Act: -0.0000

Data Index: 1477363 (Python Code)

Max Activating Token Index: 680

Text #11

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.7725. Min Act: -0.0000

Data Index: 1121253 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.5305. Min Act: -0.0000

Data Index: 910827 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.7070. Min Act: -0.0000

Data Index: 1978 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.5685. Min Act: -0.0000

Data Index: 276647 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.6680. Min Act: -0.0000

Data Index: 221431 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.5694. Min Act: -0.0000

Data Index: 582439 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.6368. Min Act: -0.0000

Data Index: 1608973 (Python Code)

Max Activating Token Index: 753

Text #18

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.5917. Min Act: -0.0000

Data Index: 1017061 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 2.1032. Min Range: -2.1032

Max Act: 1.6250. Min Act: -0.0000

Data Index: 783783 (C4 (Web Text))

Max Activating Token Index: 633