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

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

Neuron 1617 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.6666. Min Act: -0.0000

Data Index: 1582638 (Python Code)

Max Activating Token Index: 127

Text #1

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.5970. Min Act: -0.0000

Data Index: 1627721 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.3933. Min Act: -0.0000

Data Index: 1621691 (Python Code)

Max Activating Token Index: 1020

Text #3

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.3107. Min Act: -0.0000

Data Index: 1520970 (Python Code)

Max Activating Token Index: 733

Text #4

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1656887 (Python Code)

Max Activating Token Index: 421

Text #5

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.1589. Min Act: -0.0000

Data Index: 1454850 (Python Code)

Max Activating Token Index: 854

Text #6

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1616217 (Python Code)

Max Activating Token Index: 710

Text #7

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1366840 (Python Code)

Max Activating Token Index: 249

Text #8

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1516933 (Python Code)

Max Activating Token Index: 947

Text #9

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1362222 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1636979 (Python Code)

Max Activating Token Index: 867

Text #11

Max Range: 1.6666. Min Range: -1.6666

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1382911 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 1.6666. Min Range: -1.6666

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1463747 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 1.6666. Min Range: -1.6666

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1548369 (Python Code)

Max Activating Token Index: 357

Text #14

Max Range: 1.6666. Min Range: -1.6666

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1474840 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1587309 (Python Code)

Max Activating Token Index: 569

Text #16

Max Range: 1.6666. Min Range: -1.6666

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1397008 (Python Code)

Max Activating Token Index: 621

Text #17

Max Range: 1.6666. Min Range: -1.6666

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1486619 (Python Code)

Max Activating Token Index: 239

Text #18

Max Range: 1.6666. Min Range: -1.6666

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1649156 (Python Code)

Max Activating Token Index: 918

Text #19

Max Range: 1.6666. Min Range: -1.6666

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1491256 (Python Code)

Max Activating Token Index: 390