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

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

Neuron 1480 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.8296. Min Act: -0.0004

Data Index: 1585572 (Python Code)

Max Activating Token Index: 106

Text #1

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7728. Min Act: -0.0004

Data Index: 1436257 (Python Code)

Max Activating Token Index: 994

Text #2

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7411. Min Act: -0.0004

Data Index: 1649544 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7601. Min Act: -0.0004

Data Index: 1626545 (Python Code)

Max Activating Token Index: 997

Text #4

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6839. Min Act: -0.0004

Data Index: 1623164 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7026. Min Act: -0.0004

Data Index: 1541893 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7227. Min Act: -0.0004

Data Index: 1419670 (Python Code)

Max Activating Token Index: 224

Text #7

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6411. Min Act: -0.0004

Data Index: 1383782 (Python Code)

Max Activating Token Index: 361

Text #8

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6497. Min Act: -0.0004

Data Index: 1437551 (Python Code)

Max Activating Token Index: 599

Text #9

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6953. Min Act: -0.0004

Data Index: 1637709 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6693. Min Act: -0.0004

Data Index: 1541608 (Python Code)

Max Activating Token Index: 470

Text #11

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6593. Min Act: -0.0004

Data Index: 1592769 (Python Code)

Max Activating Token Index: 767

Text #12

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6796. Min Act: -0.0004

Data Index: 1594741 (Python Code)

Max Activating Token Index: 547

Text #13

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6507. Min Act: -0.0004

Data Index: 1645221 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6486. Min Act: -0.0004

Data Index: 1652948 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6721. Min Act: -0.0004

Data Index: 1627244 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6635. Min Act: -0.0004

Data Index: 1434075 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6641. Min Act: -0.0004

Data Index: 1450011 (Python Code)

Max Activating Token Index: 890

Text #18

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6397. Min Act: -0.0004

Data Index: 1576351 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6799. Min Act: -0.0004

Data Index: 1600349 (Python Code)

Max Activating Token Index: 17