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

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

Neuron 616 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.7013. Min Act: -0.0001

Data Index: 1535468 (Python Code)

Max Activating Token Index: 436

Text #1

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.3730. Min Act: -0.0001

Data Index: 1410624 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.5449. Min Act: -0.0001

Data Index: 1439668 (Python Code)

Max Activating Token Index: 387

Text #3

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.4249. Min Act: -0.0001

Data Index: 1438765 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.2445. Min Act: -0.0001

Data Index: 1468089 (Python Code)

Max Activating Token Index: 528

Text #5

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.5257. Min Act: -0.0001

Data Index: 1189482 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.2789. Min Act: -0.0001

Data Index: 1087100 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1607026 (Python Code)

Max Activating Token Index: 214

Text #8

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.2670. Min Act: -0.0000

Data Index: 1566190 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.3548. Min Act: -0.0000

Data Index: 1634219 (Python Code)

Max Activating Token Index: 862

Text #10

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.2516. Min Act: -0.0001

Data Index: 1596492 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.2312. Min Act: -0.0000

Data Index: 1486057 (Python Code)

Max Activating Token Index: 1013

Text #12

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.1632. Min Act: -0.0001

Data Index: 1608213 (Python Code)

Max Activating Token Index: 882

Text #13

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.0489. Min Act: -0.0001

Data Index: 1469670 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 1.7013. Min Range: -1.7013

Max Act: 0.8218. Min Act: -0.0001

Data Index: 1578004 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.2109. Min Act: -0.0001

Data Index: 1543586 (Python Code)

Max Activating Token Index: 857

Text #16

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.3049. Min Act: -0.0001

Data Index: 1466492 (Python Code)

Max Activating Token Index: 349

Text #17

Max Range: 1.7013. Min Range: -1.7013

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1607833 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.1261. Min Act: -0.0001

Data Index: 1504021 (Python Code)

Max Activating Token Index: 1002

Text #19

Max Range: 1.7013. Min Range: -1.7013

Max Act: 1.2297. Min Act: -0.0001

Data Index: 998313 (C4 (Web Text))

Max Activating Token Index: 558