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

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

Neuron 2751 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: 0.9491. Min Range: -0.9491

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1490083 (Python Code)

Max Activating Token Index: 763

Text #1

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1654214 (Python Code)

Max Activating Token Index: 166

Text #2

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.8205. Min Act: -0.0001

Data Index: 1396519 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1426854 (Python Code)

Max Activating Token Index: 146

Text #4

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1585215 (Python Code)

Max Activating Token Index: 321

Text #5

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1522728 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1592781 (Python Code)

Max Activating Token Index: 941

Text #7

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1468677 (Python Code)

Max Activating Token Index: 622

Text #8

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1482479 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1509964 (Python Code)

Max Activating Token Index: 980

Text #10

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1425921 (Python Code)

Max Activating Token Index: 334

Text #11

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1427515 (Python Code)

Max Activating Token Index: 183

Text #12

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6502. Min Act: -0.0001

Data Index: 980448 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1427281 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6543. Min Act: -0.0001

Data Index: 1535839 (Python Code)

Max Activating Token Index: 945

Text #15

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1623422 (Python Code)

Max Activating Token Index: 285

Text #16

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6521. Min Act: -0.0001

Data Index: 1591663 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1476933 (Python Code)

Max Activating Token Index: 36

Text #18

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1489156 (Python Code)

Max Activating Token Index: 896

Text #19

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6735. Min Act: -0.0001

Data Index: 1600710 (Python Code)

Max Activating Token Index: 48