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

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

Neuron 326 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: 0.0830. Min Range: -0.0830

Max Act: 0.0824. Min Act: -0.0003

Data Index: 1652716 (Python Code)

Max Activating Token Index: 341

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0003

Data Index: 1568375 (Python Code)

Max Activating Token Index: 118

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0770. Min Act: -0.0003

Data Index: 1516702 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0775. Min Act: -0.0003

Data Index: 1552307 (Python Code)

Max Activating Token Index: 997

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0755. Min Act: -0.0003

Data Index: 1527292 (Python Code)

Max Activating Token Index: 289

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0732. Min Act: -0.0003

Data Index: 1556755 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0722. Min Act: -0.0003

Data Index: 1477981 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1432417 (Python Code)

Max Activating Token Index: 948

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1365438 (Python Code)

Max Activating Token Index: 920

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0679. Min Act: -0.0003

Data Index: 1655551 (Python Code)

Max Activating Token Index: 307

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1551202 (Python Code)

Max Activating Token Index: 490

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0678. Min Act: -0.0003

Data Index: 1489223 (Python Code)

Max Activating Token Index: 821

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1651086 (Python Code)

Max Activating Token Index: 804

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1531825 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1471204 (Python Code)

Max Activating Token Index: 295

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1361821 (Python Code)

Max Activating Token Index: 819

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0624. Min Act: -0.0003

Data Index: 1394387 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1515533 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1478066 (Python Code)

Max Activating Token Index: 643

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1455983 (Python Code)

Max Activating Token Index: 757