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

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

Neuron 4830 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.3273. Min Act: -0.0000

Data Index: 858728 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.2371. Min Act: -0.0000

Data Index: 306290 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1976. Min Act: -0.0000

Data Index: 442068 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0081. Min Act: -0.0000

Data Index: 862001 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0660. Min Act: -0.0000

Data Index: 311568 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9519. Min Act: -0.0000

Data Index: 82684 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0117. Min Act: -0.0000

Data Index: 572735 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0251. Min Act: -0.0000

Data Index: 483971 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1119490 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1012813 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.8831. Min Act: -0.0000

Data Index: 872213 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.8753. Min Act: -0.0000

Data Index: 477903 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9485. Min Act: -0.0000

Data Index: 775866 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.8367. Min Act: -0.0000

Data Index: 750622 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.8637. Min Act: -0.0000

Data Index: 524194 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.8776. Min Act: -0.0000

Data Index: 829851 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9256. Min Act: -0.0000

Data Index: 171410 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1271184 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9117. Min Act: -0.0000

Data Index: 495874 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1294280 (C4 (Web Text))

Max Activating Token Index: 370