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

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

Neuron 2876 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.8919. Min Act: -0.0002

Data Index: 1625932 (Python Code)

Max Activating Token Index: 107

Text #1

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.6925. Min Act: -0.0002

Data Index: 1566898 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.6937. Min Act: -0.0002

Data Index: 1417717 (Python Code)

Max Activating Token Index: 856

Text #3

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.6866. Min Act: -0.0002

Data Index: 1626947 (Python Code)

Max Activating Token Index: 725

Text #4

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.5891. Min Act: -0.0002

Data Index: 1384703 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.5370. Min Act: -0.0002

Data Index: 1419726 (Python Code)

Max Activating Token Index: 269

Text #6

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.4469. Min Act: -0.0002

Data Index: 1434010 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.5668. Min Act: -0.0002

Data Index: 1363424 (Python Code)

Max Activating Token Index: 633

Text #8

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.5593. Min Act: -0.0002

Data Index: 1380801 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.6443. Min Act: -0.0002

Data Index: 1644743 (Python Code)

Max Activating Token Index: 709

Text #10

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.5699. Min Act: -0.0002

Data Index: 1620398 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.6984. Min Act: -0.0002

Data Index: 1562359 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.3686. Min Act: -0.0002

Data Index: 1551710 (Python Code)

Max Activating Token Index: 693

Text #13

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.5455. Min Act: -0.0002

Data Index: 1459809 (Python Code)

Max Activating Token Index: 395

Text #14

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.2514. Min Act: -0.0002

Data Index: 1382196 (Python Code)

Max Activating Token Index: 685

Text #15

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.6240. Min Act: -0.0002

Data Index: 1373642 (Python Code)

Max Activating Token Index: 237

Text #16

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.5835. Min Act: -0.0002

Data Index: 1637949 (Python Code)

Max Activating Token Index: 902

Text #17

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.7411. Min Act: -0.0002

Data Index: 1449915 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.6452. Min Act: -0.0002

Data Index: 1456235 (Python Code)

Max Activating Token Index: 486

Text #19

Max Range: 1.8919. Min Range: -1.8919

Max Act: 1.2732. Min Act: -0.0002

Data Index: 1619575 (Python Code)

Max Activating Token Index: 211