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

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

Neuron 2285 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.1028. Min Act: -0.0004

Data Index: 655543 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0574. Min Act: -0.0004

Data Index: 1375545 (Python Code)

Max Activating Token Index: 647

Text #2

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0616. Min Act: -0.0004

Data Index: 1647089 (Python Code)

Max Activating Token Index: 675

Text #3

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0540. Min Act: -0.0004

Data Index: 1368412 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0441. Min Act: -0.0004

Data Index: 606867 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0419. Min Act: -0.0004

Data Index: 238003 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0454. Min Act: -0.0004

Data Index: 1507328 (Python Code)

Max Activating Token Index: 914

Text #7

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0417. Min Act: -0.0004

Data Index: 27370 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0386. Min Act: -0.0004

Data Index: 557620 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0412. Min Act: -0.0004

Data Index: 1577207 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0354. Min Act: -0.0004

Data Index: 1621218 (Python Code)

Max Activating Token Index: 203

Text #11

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0319. Min Act: -0.0004

Data Index: 1484277 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0312. Min Act: -0.0004

Data Index: 1528078 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0322. Min Act: -0.0004

Data Index: 705799 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0336. Min Act: -0.0004

Data Index: 691670 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0305. Min Act: -0.0004

Data Index: 1132213 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0298. Min Act: -0.0004

Data Index: 1107494 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0309. Min Act: -0.0004

Data Index: 1420617 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1566027 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0274. Min Act: -0.0004

Data Index: 1476722 (Python Code)

Max Activating Token Index: 575