Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1768 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.1133. Min Act: -0.0003

Data Index: 543038 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.1022. Min Act: -0.0003

Data Index: 1495296 (Python Code)

Max Activating Token Index: 578

Text #2

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0925. Min Act: -0.0003

Data Index: 1568733 (Python Code)

Max Activating Token Index: 139

Text #3

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0861. Min Act: -0.0003

Data Index: 1511373 (Python Code)

Max Activating Token Index: 674

Text #4

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1414347 (Python Code)

Max Activating Token Index: 279

Text #5

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0803. Min Act: -0.0003

Data Index: 1496827 (Python Code)

Max Activating Token Index: 626

Text #6

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0796. Min Act: -0.0003

Data Index: 1524889 (Python Code)

Max Activating Token Index: 522

Text #7

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0784. Min Act: -0.0003

Data Index: 458340 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0780. Min Act: -0.0003

Data Index: 1447843 (Python Code)

Max Activating Token Index: 912

Text #9

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0792. Min Act: -0.0003

Data Index: 1494044 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0780. Min Act: -0.0003

Data Index: 1494610 (Python Code)

Max Activating Token Index: 548

Text #11

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0759. Min Act: -0.0003

Data Index: 1538933 (Python Code)

Max Activating Token Index: 321

Text #12

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0779. Min Act: -0.0003

Data Index: 1633922 (Python Code)

Max Activating Token Index: 339

Text #13

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0753. Min Act: -0.0003

Data Index: 1455993 (Python Code)

Max Activating Token Index: 315

Text #14

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1505470 (Python Code)

Max Activating Token Index: 879

Text #15

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0732. Min Act: -0.0003

Data Index: 1500094 (Python Code)

Max Activating Token Index: 526

Text #16

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1627863 (Python Code)

Max Activating Token Index: 567

Text #17

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1615551 (Python Code)

Max Activating Token Index: 303

Text #18

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1586293 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1503451 (Python Code)

Max Activating Token Index: 476