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

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

Neuron 4016 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: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0000

Data Index: 643592 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1556460 (Python Code)

Max Activating Token Index: 337

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1390178 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1491852 (Python Code)

Max Activating Token Index: 825

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1384739 (Python Code)

Max Activating Token Index: 175

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1481724 (Python Code)

Max Activating Token Index: 585

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0834. Min Act: -0.0000

Data Index: 34917 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1469668 (Python Code)

Max Activating Token Index: 574

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0822. Min Act: -0.0000

Data Index: 723078 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1480091 (Python Code)

Max Activating Token Index: 275

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1548691 (Python Code)

Max Activating Token Index: 118

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1498981 (Python Code)

Max Activating Token Index: 758

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0791. Min Act: -0.0000

Data Index: 354438 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1340728 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0823. Min Act: -0.0000

Data Index: 683239 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0785. Min Act: -0.0000

Data Index: 587822 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0815. Min Act: -0.0000

Data Index: 820886 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1125822 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1487680 (Python Code)

Max Activating Token Index: 861

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1561476 (Python Code)

Max Activating Token Index: 342