Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3298 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.8269. Min Act: -0.0000

Data Index: 1531850 (Python Code)

Max Activating Token Index: 129

Text #1

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.9782. Min Act: -0.0000

Data Index: 1400805 (Python Code)

Max Activating Token Index: 523

Text #2

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.7653. Min Act: -0.0000

Data Index: 1383532 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6461. Min Act: -0.0000

Data Index: 1630648 (Python Code)

Max Activating Token Index: 777

Text #4

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.9263. Min Act: -0.0000

Data Index: 1559135 (Python Code)

Max Activating Token Index: 939

Text #5

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.7114. Min Act: -0.0001

Data Index: 1497425 (Python Code)

Max Activating Token Index: 432

Text #6

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5912. Min Act: -0.0001

Data Index: 1621693 (Python Code)

Max Activating Token Index: 381

Text #7

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6775. Min Act: -0.0000

Data Index: 1585395 (Python Code)

Max Activating Token Index: 876

Text #8

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6576. Min Act: -0.0001

Data Index: 1586042 (Python Code)

Max Activating Token Index: 516

Text #9

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.7460. Min Act: -0.0000

Data Index: 1614003 (Python Code)

Max Activating Token Index: 83

Text #10

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6452. Min Act: -0.0000

Data Index: 1636490 (Python Code)

Max Activating Token Index: 177

Text #11

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6990. Min Act: -0.0001

Data Index: 1626811 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5086. Min Act: -0.0000

Data Index: 1499752 (Python Code)

Max Activating Token Index: 968

Text #13

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5902. Min Act: -0.0000

Data Index: 1428155 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.7623. Min Act: -0.0000

Data Index: 1474800 (Python Code)

Max Activating Token Index: 321

Text #15

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.7037. Min Act: -0.0000

Data Index: 1412971 (Python Code)

Max Activating Token Index: 726

Text #16

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1394282 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1569736 (Python Code)

Max Activating Token Index: 96

Text #18

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5053. Min Act: -0.0000

Data Index: 1497260 (Python Code)

Max Activating Token Index: 283

Text #19

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5467. Min Act: -0.0000

Data Index: 1568370 (Python Code)

Max Activating Token Index: 580