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

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

Neuron 872 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: 0.0474. Min Range: -0.0474

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1509256 (Python Code)

Max Activating Token Index: 488

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1514655 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1492089 (Python Code)

Max Activating Token Index: 908

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1410899 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1464447 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1453385 (Python Code)

Max Activating Token Index: 960

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1444878 (Python Code)

Max Activating Token Index: 826

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1551807 (Python Code)

Max Activating Token Index: 758

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1433191 (Python Code)

Max Activating Token Index: 126

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1611531 (Python Code)

Max Activating Token Index: 794

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1499895 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1440496 (Python Code)

Max Activating Token Index: 335

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1363032 (Python Code)

Max Activating Token Index: 654

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1395771 (Python Code)

Max Activating Token Index: 886

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1607057 (Python Code)

Max Activating Token Index: 781

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1629722 (Python Code)

Max Activating Token Index: 362

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1635470 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1610437 (Python Code)

Max Activating Token Index: 776

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1476802 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1476733 (Python Code)

Max Activating Token Index: 862