Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1528 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.7496. Min Act: -0.0001

Data Index: 1504227 (Python Code)

Max Activating Token Index: 843

Text #1

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.6651. Min Act: -0.0000

Data Index: 1492640 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1592819 (Python Code)

Max Activating Token Index: 100

Text #3

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1607316 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.3026. Min Act: -0.0000

Data Index: 1607896 (Python Code)

Max Activating Token Index: 972

Text #5

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.3519. Min Act: -0.0000

Data Index: 1569476 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1151386 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.4109. Min Act: -0.0001

Data Index: 206900 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1439891 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1656450 (Python Code)

Max Activating Token Index: 424

Text #10

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1442701 (Python Code)

Max Activating Token Index: 175

Text #11

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.2844. Min Act: -0.0000

Data Index: 1066342 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1382218 (Python Code)

Max Activating Token Index: 99

Text #13

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1485160 (Python Code)

Max Activating Token Index: 61

Text #14

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.2488. Min Act: -0.0001

Data Index: 1118500 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1565145 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.2444. Min Act: -0.0000

Data Index: 1538381 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.2851. Min Act: -0.0000

Data Index: 1406275 (Python Code)

Max Activating Token Index: 916

Text #18

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.1333. Min Act: -0.0000

Data Index: 1495415 (Python Code)

Max Activating Token Index: 450

Text #19

Max Range: 1.7496. Min Range: -1.7496

Max Act: 1.1907. Min Act: -0.0001

Data Index: 1448245 (Python Code)

Max Activating Token Index: 552