Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1648 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8893. Min Act: -0.0001

Data Index: 1404621 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8680. Min Act: -0.0001

Data Index: 1535983 (Python Code)

Max Activating Token Index: 655

Text #2

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8425. Min Act: -0.0001

Data Index: 1517619 (Python Code)

Max Activating Token Index: 468

Text #3

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8330. Min Act: -0.0001

Data Index: 1497666 (Python Code)

Max Activating Token Index: 328

Text #4

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8319. Min Act: -0.0001

Data Index: 1443359 (Python Code)

Max Activating Token Index: 468

Text #5

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8047. Min Act: -0.0001

Data Index: 1640637 (Python Code)

Max Activating Token Index: 611

Text #6

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1414904 (Python Code)

Max Activating Token Index: 143

Text #7

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7423. Min Act: -0.0001

Data Index: 1559254 (Python Code)

Max Activating Token Index: 774

Text #8

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7381. Min Act: -0.0001

Data Index: 1483705 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7185. Min Act: -0.0001

Data Index: 1543870 (Python Code)

Max Activating Token Index: 836

Text #10

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7426. Min Act: -0.0001

Data Index: 1516727 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7325. Min Act: -0.0001

Data Index: 1513241 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7394. Min Act: -0.0001

Data Index: 1534164 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7106. Min Act: -0.0001

Data Index: 1391593 (Python Code)

Max Activating Token Index: 894

Text #14

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7295. Min Act: -0.0001

Data Index: 1383307 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7082. Min Act: -0.0001

Data Index: 1539976 (Python Code)

Max Activating Token Index: 656

Text #16

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7079. Min Act: -0.0001

Data Index: 1573676 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7241. Min Act: -0.0001

Data Index: 1422337 (Python Code)

Max Activating Token Index: 617

Text #18

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7308. Min Act: -0.0001

Data Index: 1411037 (Python Code)

Max Activating Token Index: 704

Text #19

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7080. Min Act: -0.0001

Data Index: 1592819 (Python Code)

Max Activating Token Index: 23