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

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

Neuron 4483 in Layer 0

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: 0.8687. Min Range: -0.8687

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1366198 (Python Code)

Max Activating Token Index: 159

Text #1

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8512. Min Act: -0.0001

Data Index: 1566163 (Python Code)

Max Activating Token Index: 758

Text #2

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8687. Min Act: -0.0001

Data Index: 1546416 (Python Code)

Max Activating Token Index: 931

Text #3

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8402. Min Act: -0.0001

Data Index: 1524407 (Python Code)

Max Activating Token Index: 78

Text #4

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8404. Min Act: -0.0002

Data Index: 1394706 (Python Code)

Max Activating Token Index: 780

Text #5

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8403. Min Act: -0.0001

Data Index: 1571296 (Python Code)

Max Activating Token Index: 1007

Text #6

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8421. Min Act: -0.0001

Data Index: 1520656 (Python Code)

Max Activating Token Index: 1020

Text #7

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8540. Min Act: -0.0001

Data Index: 1433848 (Python Code)

Max Activating Token Index: 833

Text #8

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8213. Min Act: -0.0001

Data Index: 1586155 (Python Code)

Max Activating Token Index: 904

Text #9

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8263. Min Act: -0.0001

Data Index: 1533028 (Python Code)

Max Activating Token Index: 900

Text #10

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8260. Min Act: -0.0001

Data Index: 1546861 (Python Code)

Max Activating Token Index: 929

Text #11

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8075. Min Act: -0.0001

Data Index: 1474597 (Python Code)

Max Activating Token Index: 667

Text #12

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8248. Min Act: -0.0001

Data Index: 1380557 (Python Code)

Max Activating Token Index: 847

Text #13

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8345. Min Act: -0.0001

Data Index: 1416401 (Python Code)

Max Activating Token Index: 388

Text #14

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8098. Min Act: -0.0001

Data Index: 1593910 (Python Code)

Max Activating Token Index: 832

Text #15

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1549919 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8376. Min Act: -0.0001

Data Index: 1392499 (Python Code)

Max Activating Token Index: 836

Text #17

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8246. Min Act: -0.0001

Data Index: 1409688 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.7863. Min Act: -0.0001

Data Index: 1428960 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.7847. Min Act: -0.0001

Data Index: 1409230 (Python Code)

Max Activating Token Index: 1014