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

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

Neuron 2694 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1647. Min Range: -1.1647

Max Act: 1.1647. Min Act: -0.0001

Data Index: 1519099 (Python Code)

Max Activating Token Index: 252

Text #1

Max Range: 1.1647. Min Range: -1.1647

Max Act: 1.1453. Min Act: -0.0001

Data Index: 1646437 (Python Code)

Max Activating Token Index: 167

Text #2

Max Range: 1.1647. Min Range: -1.1647

Max Act: 1.0249. Min Act: -0.0001

Data Index: 1550107 (Python Code)

Max Activating Token Index: 743

Text #3

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.9217. Min Act: -0.0001

Data Index: 1461950 (Python Code)

Max Activating Token Index: 708

Text #4

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.8668. Min Act: -0.0001

Data Index: 1427590 (Python Code)

Max Activating Token Index: 150

Text #5

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.8903. Min Act: -0.0001

Data Index: 1366274 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7888. Min Act: -0.0001

Data Index: 1465280 (Python Code)

Max Activating Token Index: 265

Text #7

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.8518. Min Act: -0.0001

Data Index: 1656251 (Python Code)

Max Activating Token Index: 833

Text #8

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.8684. Min Act: -0.0001

Data Index: 1471505 (Python Code)

Max Activating Token Index: 919

Text #9

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7439. Min Act: -0.0001

Data Index: 1418140 (Python Code)

Max Activating Token Index: 579

Text #10

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.8200. Min Act: -0.0001

Data Index: 1625063 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.8367. Min Act: -0.0001

Data Index: 1586045 (Python Code)

Max Activating Token Index: 308

Text #12

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7540. Min Act: -0.0001

Data Index: 1648398 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1466667 (Python Code)

Max Activating Token Index: 92

Text #14

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7921. Min Act: -0.0001

Data Index: 1510098 (Python Code)

Max Activating Token Index: 994

Text #15

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7062. Min Act: -0.0001

Data Index: 1640493 (Python Code)

Max Activating Token Index: 295

Text #16

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7731. Min Act: -0.0001

Data Index: 1564647 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1529857 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7865. Min Act: -0.0001

Data Index: 1649891 (Python Code)

Max Activating Token Index: 1020

Text #19

Max Range: 1.1647. Min Range: -1.1647

Max Act: 0.7229. Min Act: -0.0001

Data Index: 1655907 (Python Code)

Max Activating Token Index: 596