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

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

Neuron 3092 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7513. Min Range: -2.7513

Max Act: 2.7513. Min Act: -0.0000

Data Index: 1654729 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 2.7513. Min Range: -2.7513

Max Act: 2.3203. Min Act: -0.0000

Data Index: 1417804 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.5811. Min Act: -0.0000

Data Index: 1633794 (Python Code)

Max Activating Token Index: 823

Text #3

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.9328. Min Act: -0.0000

Data Index: 1599366 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.7953. Min Act: -0.0000

Data Index: 1455985 (Python Code)

Max Activating Token Index: 465

Text #5

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.8286. Min Act: -0.0000

Data Index: 1394910 (Python Code)

Max Activating Token Index: 1004

Text #6

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.7525. Min Act: -0.0000

Data Index: 1587629 (Python Code)

Max Activating Token Index: 483

Text #7

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.6387. Min Act: -0.0000

Data Index: 1427502 (Python Code)

Max Activating Token Index: 859

Text #8

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.6508. Min Act: -0.0000

Data Index: 1587688 (Python Code)

Max Activating Token Index: 886

Text #9

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.6243. Min Act: -0.0000

Data Index: 1593405 (Python Code)

Max Activating Token Index: 616

Text #10

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.7968. Min Act: -0.0000

Data Index: 1532774 (Python Code)

Max Activating Token Index: 647

Text #11

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1574573 (Python Code)

Max Activating Token Index: 878

Text #12

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.7044. Min Act: -0.0000

Data Index: 1545812 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.5980. Min Act: -0.0000

Data Index: 1626092 (Python Code)

Max Activating Token Index: 956

Text #14

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.5888. Min Act: -0.0000

Data Index: 1386398 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.9551. Min Act: -0.0000

Data Index: 1377403 (Python Code)

Max Activating Token Index: 740

Text #16

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.4045. Min Act: -0.0000

Data Index: 1446702 (Python Code)

Max Activating Token Index: 1012

Text #17

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.9038. Min Act: -0.0000

Data Index: 1380522 (Python Code)

Max Activating Token Index: 820

Text #18

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.5019. Min Act: -0.0000

Data Index: 1638816 (Python Code)

Max Activating Token Index: 822

Text #19

Max Range: 2.7513. Min Range: -2.7513

Max Act: 1.6132. Min Act: -0.0000

Data Index: 1596412 (Python Code)

Max Activating Token Index: 545