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

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

Neuron 4965 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2636. Min Range: -3.2636

Max Act: 3.2636. Min Act: -0.0000

Data Index: 434253 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 3.2636. Min Range: -3.2636

Max Act: 3.1473. Min Act: -0.0000

Data Index: 171562 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.2636. Min Range: -3.2636

Max Act: 3.0983. Min Act: -0.0000

Data Index: 797576 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 3.2636. Min Range: -3.2636

Max Act: 3.0346. Min Act: -0.0000

Data Index: 485106 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.9644. Min Act: -0.0000

Data Index: 463980 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.9582. Min Act: -0.0000

Data Index: 777965 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.8488. Min Act: -0.0000

Data Index: 131129 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.7071. Min Act: -0.0000

Data Index: 54084 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.9780. Min Act: -0.0000

Data Index: 775071 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.8361. Min Act: -0.0000

Data Index: 479137 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.7990. Min Act: -0.0000

Data Index: 1006122 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.9410. Min Act: -0.0000

Data Index: 241103 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.6578. Min Act: -0.0000

Data Index: 395127 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.9179. Min Act: -0.0000

Data Index: 1156742 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.6351. Min Act: -0.0000

Data Index: 637 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.7613. Min Act: -0.0000

Data Index: 557314 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.7696. Min Act: -0.0000

Data Index: 947963 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.7677. Min Act: -0.0000

Data Index: 1289140 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.6346. Min Act: -0.0000

Data Index: 818447 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 3.2636. Min Range: -3.2636

Max Act: 2.5830. Min Act: -0.0000

Data Index: 1117324 (C4 (Web Text))

Max Activating Token Index: 118