Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2379 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.8757. Min Act: -0.0001

Data Index: 1425171 (Python Code)

Max Activating Token Index: 561

Text #1

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1625530 (Python Code)

Max Activating Token Index: 108

Text #2

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.6651. Min Act: -0.0001

Data Index: 1593452 (Python Code)

Max Activating Token Index: 789

Text #3

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5908. Min Act: -0.0001

Data Index: 1546643 (Python Code)

Max Activating Token Index: 176

Text #4

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1596701 (Python Code)

Max Activating Token Index: 988

Text #5

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5601. Min Act: -0.0001

Data Index: 1583575 (Python Code)

Max Activating Token Index: 457

Text #6

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1373847 (Python Code)

Max Activating Token Index: 652

Text #7

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5510. Min Act: -0.0001

Data Index: 1380193 (Python Code)

Max Activating Token Index: 605

Text #8

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5559. Min Act: -0.0001

Data Index: 1395895 (Python Code)

Max Activating Token Index: 465

Text #9

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5088. Min Act: -0.0001

Data Index: 1522045 (Python Code)

Max Activating Token Index: 195

Text #10

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1528212 (Python Code)

Max Activating Token Index: 582

Text #11

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5392. Min Act: -0.0001

Data Index: 1456937 (Python Code)

Max Activating Token Index: 683

Text #12

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5283. Min Act: -0.0001

Data Index: 1489884 (Python Code)

Max Activating Token Index: 519

Text #13

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5298. Min Act: -0.0001

Data Index: 1495527 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1589234 (Python Code)

Max Activating Token Index: 394

Text #15

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1517581 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5227. Min Act: -0.0001

Data Index: 1401060 (Python Code)

Max Activating Token Index: 68

Text #17

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1540456 (Python Code)

Max Activating Token Index: 881

Text #18

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1571030 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 0.8757. Min Range: -0.8757

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1548307 (Python Code)

Max Activating Token Index: 714