Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1009 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.9410. Min Act: -0.0001

Data Index: 675269 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4516. Min Act: -0.0001

Data Index: 1621548 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.6370. Min Act: -0.0001

Data Index: 1483945 (Python Code)

Max Activating Token Index: 54

Text #3

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.5759. Min Act: -0.0001

Data Index: 1375545 (Python Code)

Max Activating Token Index: 964

Text #4

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.5276. Min Act: -0.0001

Data Index: 1614094 (Python Code)

Max Activating Token Index: 111

Text #5

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.5580. Min Act: -0.0001

Data Index: 198463 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.4924. Min Act: -0.0001

Data Index: 963575 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2758. Min Act: -0.0001

Data Index: 1553744 (Python Code)

Max Activating Token Index: 902

Text #8

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3386. Min Act: -0.0001

Data Index: 1217610 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2753. Min Act: -0.0001

Data Index: 914413 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3258. Min Act: -0.0001

Data Index: 1535780 (Python Code)

Max Activating Token Index: 424

Text #11

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3106. Min Act: -0.0001

Data Index: 1160184 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2359. Min Act: -0.0001

Data Index: 1615736 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3304. Min Act: -0.0001

Data Index: 532409 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3227. Min Act: -0.0001

Data Index: 316122 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.3892. Min Act: -0.0001

Data Index: 1608980 (Python Code)

Max Activating Token Index: 984

Text #16

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2561. Min Act: -0.0001

Data Index: 145730 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2766. Min Act: -0.0001

Data Index: 206123 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.1944. Min Act: -0.0001

Data Index: 1586022 (Python Code)

Max Activating Token Index: 700

Text #19

Max Range: 1.9410. Min Range: -1.9410

Max Act: 1.2938. Min Act: -0.0001

Data Index: 408043 (C4 (Web Text))

Max Activating Token Index: 14