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

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

Neuron 1408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1046. Min Range: -1.1046

Max Act: 1.1046. Min Act: -0.0001

Data Index: 1366023 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8637. Min Act: -0.0001

Data Index: 1406836 (Python Code)

Max Activating Token Index: 867

Text #2

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9097. Min Act: -0.0001

Data Index: 1438394 (Python Code)

Max Activating Token Index: 285

Text #3

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1523159 (Python Code)

Max Activating Token Index: 768

Text #4

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8290. Min Act: -0.0001

Data Index: 1615701 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8427. Min Act: -0.0001

Data Index: 1510600 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8979. Min Act: -0.0001

Data Index: 1541055 (Python Code)

Max Activating Token Index: 848

Text #7

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8692. Min Act: -0.0001

Data Index: 1610526 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7986. Min Act: -0.0001

Data Index: 1571633 (Python Code)

Max Activating Token Index: 327

Text #9

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7475. Min Act: -0.0001

Data Index: 1467405 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7658. Min Act: -0.0001

Data Index: 1576098 (Python Code)

Max Activating Token Index: 1013

Text #11

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8543. Min Act: -0.0001

Data Index: 1474099 (Python Code)

Max Activating Token Index: 981

Text #12

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7504. Min Act: -0.0001

Data Index: 1575350 (Python Code)

Max Activating Token Index: 386

Text #13

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7732. Min Act: -0.0001

Data Index: 1566785 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7180. Min Act: -0.0001

Data Index: 1552803 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7635. Min Act: -0.0001

Data Index: 1468534 (Python Code)

Max Activating Token Index: 717

Text #16

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7900. Min Act: -0.0001

Data Index: 1393613 (Python Code)

Max Activating Token Index: 727

Text #17

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7365. Min Act: -0.0001

Data Index: 1428909 (Python Code)

Max Activating Token Index: 840

Text #18

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7336. Min Act: -0.0001

Data Index: 1564267 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7546. Min Act: -0.0001

Data Index: 1369063 (Python Code)

Max Activating Token Index: 99