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

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

Neuron 1518 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.4650. Min Act: -0.0001

Data Index: 1594398 (Python Code)

Max Activating Token Index: 886

Text #1

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.3332. Min Act: -0.0001

Data Index: 1539940 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.3485. Min Act: -0.0001

Data Index: 1430201 (Python Code)

Max Activating Token Index: 923

Text #3

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1362211 (Python Code)

Max Activating Token Index: 337

Text #4

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.3156. Min Act: -0.0001

Data Index: 1621618 (Python Code)

Max Activating Token Index: 934

Text #5

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.3131. Min Act: -0.0001

Data Index: 1581500 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.3040. Min Act: -0.0001

Data Index: 1469948 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.4312. Min Act: -0.0001

Data Index: 1654722 (Python Code)

Max Activating Token Index: 304

Text #8

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.3360. Min Act: -0.0001

Data Index: 1585594 (Python Code)

Max Activating Token Index: 521

Text #9

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1898. Min Act: -0.0001

Data Index: 1552855 (Python Code)

Max Activating Token Index: 639

Text #10

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2609. Min Act: -0.0001

Data Index: 1519438 (Python Code)

Max Activating Token Index: 914

Text #11

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2573. Min Act: -0.0001

Data Index: 1610270 (Python Code)

Max Activating Token Index: 425

Text #12

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.1838. Min Act: -0.0001

Data Index: 1576410 (Python Code)

Max Activating Token Index: 652

Text #13

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2573. Min Act: -0.0001

Data Index: 1626010 (Python Code)

Max Activating Token Index: 686

Text #14

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1487308 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2473. Min Act: -0.0001

Data Index: 1562906 (Python Code)

Max Activating Token Index: 432

Text #16

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2375. Min Act: -0.0001

Data Index: 1554525 (Python Code)

Max Activating Token Index: 907

Text #17

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.3669. Min Act: -0.0001

Data Index: 1562283 (Python Code)

Max Activating Token Index: 840

Text #18

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2308. Min Act: -0.0001

Data Index: 1415418 (Python Code)

Max Activating Token Index: 68

Text #19

Max Range: 1.4650. Min Range: -1.4650

Max Act: 1.2257. Min Act: -0.0001

Data Index: 1618707 (Python Code)

Max Activating Token Index: 10