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

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

Neuron 920 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4218. Min Act: -0.0001

Data Index: 1458374 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4128. Min Act: -0.0001

Data Index: 1517935 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4110. Min Act: -0.0001

Data Index: 1438839 (Python Code)

Max Activating Token Index: 643

Text #3

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4235. Min Act: -0.0001

Data Index: 1629673 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3738. Min Act: -0.0001

Data Index: 1623845 (Python Code)

Max Activating Token Index: 601

Text #5

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3863. Min Act: -0.0001

Data Index: 1573972 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3876. Min Act: -0.0001

Data Index: 1570152 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4116. Min Act: -0.0001

Data Index: 1645623 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3940. Min Act: -0.0001

Data Index: 1454840 (Python Code)

Max Activating Token Index: 375

Text #9

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3950. Min Act: -0.0001

Data Index: 1533806 (Python Code)

Max Activating Token Index: 530

Text #10

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4033. Min Act: -0.0001

Data Index: 1403403 (Python Code)

Max Activating Token Index: 740

Text #11

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3999. Min Act: -0.0001

Data Index: 1637729 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4004. Min Act: -0.0000

Data Index: 126823 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4088. Min Act: -0.0001

Data Index: 1553787 (Python Code)

Max Activating Token Index: 716

Text #14

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3835. Min Act: -0.0001

Data Index: 1631527 (Python Code)

Max Activating Token Index: 435

Text #15

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3843. Min Act: -0.0001

Data Index: 1569267 (Python Code)

Max Activating Token Index: 518

Text #16

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3557. Min Act: -0.0001

Data Index: 1604728 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3645. Min Act: -0.0001

Data Index: 1404676 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3650. Min Act: -0.0001

Data Index: 1628294 (Python Code)

Max Activating Token Index: 635

Text #19

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3908. Min Act: -0.0001

Data Index: 1573490 (Python Code)

Max Activating Token Index: 248