Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3128 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1468781 (Python Code)

Max Activating Token Index: 275

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1645576 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1534956 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1437922 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1630039 (Python Code)

Max Activating Token Index: 342

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1568716 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1459629 (Python Code)

Max Activating Token Index: 369

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1596647 (Python Code)

Max Activating Token Index: 876

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1596098 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1470545 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1487069 (Python Code)

Max Activating Token Index: 382

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1366741 (Python Code)

Max Activating Token Index: 941

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1522354 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1485540 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1432383 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1607592 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1522626 (Python Code)

Max Activating Token Index: 284

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1405930 (Python Code)

Max Activating Token Index: 292

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1656700 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1655037 (Python Code)

Max Activating Token Index: 99