Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3912 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2127. Min Act: -0.0002

Data Index: 1102542 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.2127. Min Act: -0.0001

Data Index: 1513175 (Python Code)

Max Activating Token Index: 2

Text #2

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1379038 (Python Code)

Max Activating Token Index: 1008

Text #3

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1613030 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1518594 (Python Code)

Max Activating Token Index: 272

Text #5

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1544. Min Act: -0.0002

Data Index: 801335 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1154007 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1482237 (Python Code)

Max Activating Token Index: 561

Text #8

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1278523 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1484. Min Act: -0.0002

Data Index: 1087741 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1615025 (Python Code)

Max Activating Token Index: 242

Text #11

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1394445 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1468. Min Act: -0.0002

Data Index: 1204104 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1559453 (Python Code)

Max Activating Token Index: 90

Text #14

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1356421 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1414496 (Python Code)

Max Activating Token Index: 923

Text #16

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1397. Min Act: -0.0001

Data Index: 1555834 (Python Code)

Max Activating Token Index: 1012

Text #17

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1342. Min Act: -0.0001

Data Index: 364501 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1416653 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 0.2127. Min Range: -0.2127

Max Act: 0.1323. Min Act: -0.0002

Data Index: 997024 (C4 (Web Text))

Max Activating Token Index: 535