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

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

Neuron 494 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: 0.8259. Min Range: -0.8259

Max Act: 0.8259. Min Act: -0.0000

Data Index: 35679 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6974. Min Act: -0.0000

Data Index: 76900 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.7424. Min Act: -0.0000

Data Index: 49223 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6199. Min Act: -0.0000

Data Index: 16425 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5785. Min Act: -0.0000

Data Index: 353677 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6061. Min Act: -0.0000

Data Index: 987591 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1027324 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5091. Min Act: -0.0000

Data Index: 467838 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5696. Min Act: -0.0000

Data Index: 304918 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1001976 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5222. Min Act: -0.0000

Data Index: 302141 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5346. Min Act: -0.0000

Data Index: 49919 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5110. Min Act: -0.0000

Data Index: 674704 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5305. Min Act: -0.0000

Data Index: 863583 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1505821 (Python Code)

Max Activating Token Index: 952

Text #15

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4821. Min Act: -0.0000

Data Index: 276206 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4782. Min Act: -0.0000

Data Index: 422418 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1478069 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4656. Min Act: -0.0000

Data Index: 575080 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4257. Min Act: -0.0000

Data Index: 735238 (C4 (Web Text))

Max Activating Token Index: 724