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

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

Neuron 320 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4018. Min Range: -3.4018

Max Act: 3.4018. Min Act: -0.0000

Data Index: 1654801 (Python Code)

Max Activating Token Index: 755

Text #1

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.9427. Min Act: -0.0000

Data Index: 1502556 (Python Code)

Max Activating Token Index: 900

Text #2

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.9583. Min Act: -0.0000

Data Index: 1531596 (Python Code)

Max Activating Token Index: 842

Text #3

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.6132. Min Act: -0.0000

Data Index: 1406768 (Python Code)

Max Activating Token Index: 684

Text #4

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.7274. Min Act: -0.0000

Data Index: 1651083 (Python Code)

Max Activating Token Index: 666

Text #5

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.4721. Min Act: -0.0000

Data Index: 1652192 (Python Code)

Max Activating Token Index: 1009

Text #6

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.5426. Min Act: -0.0000

Data Index: 1552698 (Python Code)

Max Activating Token Index: 419

Text #7

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.4686. Min Act: -0.0000

Data Index: 1483979 (Python Code)

Max Activating Token Index: 712

Text #8

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.5982. Min Act: -0.0000

Data Index: 1544507 (Python Code)

Max Activating Token Index: 978

Text #9

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.3067. Min Act: -0.0000

Data Index: 1550883 (Python Code)

Max Activating Token Index: 925

Text #10

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.3891. Min Act: -0.0000

Data Index: 1501004 (Python Code)

Max Activating Token Index: 358

Text #11

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.2675. Min Act: -0.0000

Data Index: 1397600 (Python Code)

Max Activating Token Index: 362

Text #12

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.2668. Min Act: -0.0000

Data Index: 1490983 (Python Code)

Max Activating Token Index: 505

Text #13

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.3846. Min Act: -0.0000

Data Index: 1486621 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.3742. Min Act: -0.0000

Data Index: 1588217 (Python Code)

Max Activating Token Index: 480

Text #15

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.2520. Min Act: -0.0000

Data Index: 1522267 (Python Code)

Max Activating Token Index: 147

Text #16

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.2217. Min Act: -0.0000

Data Index: 1630441 (Python Code)

Max Activating Token Index: 837

Text #17

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.4818. Min Act: -0.0000

Data Index: 1523000 (Python Code)

Max Activating Token Index: 755

Text #18

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.3385. Min Act: -0.0000

Data Index: 1472290 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 3.4018. Min Range: -3.4018

Max Act: 2.3331. Min Act: -0.0000

Data Index: 1414843 (Python Code)

Max Activating Token Index: 550