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

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

Neuron 697 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: 5.2967. Min Range: -5.2967

Max Act: 5.2967. Min Act: -0.0000

Data Index: 1578110 (Python Code)

Max Activating Token Index: 882

Text #1

Max Range: 5.2967. Min Range: -5.2967

Max Act: 4.1411. Min Act: -0.0000

Data Index: 1551407 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 5.2967. Min Range: -5.2967

Max Act: 3.5582. Min Act: -0.0000

Data Index: 1656099 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 5.2967. Min Range: -5.2967

Max Act: 3.5210. Min Act: -0.0000

Data Index: 1493305 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 5.2967. Min Range: -5.2967

Max Act: 3.5428. Min Act: -0.0000

Data Index: 1516563 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.7053. Min Act: -0.0000

Data Index: 1488713 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 5.2967. Min Range: -5.2967

Max Act: 3.1082. Min Act: -0.0000

Data Index: 1521183 (Python Code)

Max Activating Token Index: 719

Text #7

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.8724. Min Act: -0.0000

Data Index: 1592765 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.4808. Min Act: -0.0000

Data Index: 1528006 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.5092. Min Act: -0.0000

Data Index: 1373713 (Python Code)

Max Activating Token Index: 693

Text #10

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.5083. Min Act: -0.0000

Data Index: 1586890 (Python Code)

Max Activating Token Index: 598

Text #11

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.2578. Min Act: -0.0000

Data Index: 1535576 (Python Code)

Max Activating Token Index: 571

Text #12

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.2332. Min Act: -0.0000

Data Index: 1614400 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.3188. Min Act: -0.0000

Data Index: 1543274 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.3130. Min Act: -0.0000

Data Index: 1538312 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.1336. Min Act: -0.0000

Data Index: 1629827 (Python Code)

Max Activating Token Index: 402

Text #16

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.1294. Min Act: -0.0000

Data Index: 1370708 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 5.2967. Min Range: -5.2967

Max Act: 1.8514. Min Act: -0.0000

Data Index: 1646412 (Python Code)

Max Activating Token Index: 480

Text #18

Max Range: 5.2967. Min Range: -5.2967

Max Act: 2.0419. Min Act: -0.0000

Data Index: 1590951 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 5.2967. Min Range: -5.2967

Max Act: 1.8550. Min Act: -0.0000

Data Index: 1419349 (Python Code)

Max Activating Token Index: 779