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

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

Neuron 1759 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: 1.5955. Min Range: -1.5955

Max Act: 1.5927. Min Act: -0.0002

Data Index: 1484288 (Python Code)

Max Activating Token Index: 546

Text #1

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.5955. Min Act: -0.0002

Data Index: 1545002 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.4879. Min Act: -0.0002

Data Index: 1462255 (Python Code)

Max Activating Token Index: 289

Text #3

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.4915. Min Act: -0.0002

Data Index: 1572068 (Python Code)

Max Activating Token Index: 456

Text #4

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.4390. Min Act: -0.0002

Data Index: 1441773 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.4481. Min Act: -0.0002

Data Index: 1628451 (Python Code)

Max Activating Token Index: 187

Text #6

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3720. Min Act: -0.0002

Data Index: 1421766 (Python Code)

Max Activating Token Index: 437

Text #7

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.4298. Min Act: -0.0002

Data Index: 1455013 (Python Code)

Max Activating Token Index: 596

Text #8

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.4001. Min Act: -0.0002

Data Index: 1404059 (Python Code)

Max Activating Token Index: 281

Text #9

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3406. Min Act: -0.0002

Data Index: 1374288 (Python Code)

Max Activating Token Index: 738

Text #10

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3647. Min Act: -0.0002

Data Index: 1556589 (Python Code)

Max Activating Token Index: 765

Text #11

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3733. Min Act: -0.0002

Data Index: 1510779 (Python Code)

Max Activating Token Index: 793

Text #12

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3932. Min Act: -0.0002

Data Index: 1425639 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3914. Min Act: -0.0002

Data Index: 1389108 (Python Code)

Max Activating Token Index: 660

Text #14

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3357. Min Act: -0.0002

Data Index: 1596985 (Python Code)

Max Activating Token Index: 634

Text #15

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3187. Min Act: -0.0002

Data Index: 1401407 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3705. Min Act: -0.0002

Data Index: 1510033 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3377. Min Act: -0.0002

Data Index: 1475400 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.3338. Min Act: -0.0002

Data Index: 1614581 (Python Code)

Max Activating Token Index: 173

Text #19

Max Range: 1.5955. Min Range: -1.5955

Max Act: 1.2798. Min Act: -0.0002

Data Index: 1547983 (Python Code)

Max Activating Token Index: 91