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

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

Neuron 930 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: 1.3528. Min Range: -1.3528

Max Act: 1.3526. Min Act: -0.0000

Data Index: 704948 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3528. Min Act: -0.0000

Data Index: 640397 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.2067. Min Act: -0.0000

Data Index: 859412 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.1161. Min Act: -0.0000

Data Index: 197506 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0763. Min Act: -0.0000

Data Index: 776660 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.1820. Min Act: -0.0000

Data Index: 321695 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0121. Min Act: -0.0000

Data Index: 135592 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0843. Min Act: -0.0000

Data Index: 361031 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1299100 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0765. Min Act: -0.0000

Data Index: 71670 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0805. Min Act: -0.0000

Data Index: 560517 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.1346. Min Act: -0.0000

Data Index: 73531 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.9715. Min Act: -0.0000

Data Index: 70562 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0675. Min Act: -0.0000

Data Index: 462983 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0470. Min Act: -0.0000

Data Index: 877548 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0851. Min Act: -0.0000

Data Index: 942279 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.1496. Min Act: -0.0000

Data Index: 418594 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0454. Min Act: -0.0000

Data Index: 663253 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8824. Min Act: -0.0000

Data Index: 746129 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0815. Min Act: -0.0000

Data Index: 552580 (C4 (Web Text))

Max Activating Token Index: 533