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

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

Neuron 3536 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.6314. Min Act: -0.0000

Data Index: 1334760 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.6070. Min Act: -0.0000

Data Index: 1182177 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.3991. Min Act: -0.0000

Data Index: 1196237 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.3449. Min Act: -0.0000

Data Index: 1048636 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.2783. Min Act: -0.0000

Data Index: 1581813 (Python Code)

Max Activating Token Index: 116

Text #5

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1696. Min Act: -0.0000

Data Index: 919183 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1105192 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1636573 (Python Code)

Max Activating Token Index: 952

Text #8

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1557. Min Act: -0.0000

Data Index: 751797 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1418878 (Python Code)

Max Activating Token Index: 542

Text #10

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1596. Min Act: -0.0000

Data Index: 253456 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1517. Min Act: -0.0000

Data Index: 1395078 (Python Code)

Max Activating Token Index: 569

Text #12

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1390. Min Act: -0.0000

Data Index: 1473717 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1493106 (Python Code)

Max Activating Token Index: 56

Text #14

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1432488 (Python Code)

Max Activating Token Index: 696

Text #15

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1556768 (Python Code)

Max Activating Token Index: 1004

Text #16

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1411251 (Python Code)

Max Activating Token Index: 532

Text #17

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1562182 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.0995. Min Act: -0.0000

Data Index: 35128 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1502894 (Python Code)

Max Activating Token Index: 339