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

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

Neuron 5046 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: 0.5336. Min Range: -0.5336

Max Act: 0.5336. Min Act: -0.0000

Data Index: 282168 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1141145 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.5212. Min Act: -0.0000

Data Index: 355538 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.4756. Min Act: -0.0000

Data Index: 349290 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.5200. Min Act: -0.0000

Data Index: 783283 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.4372. Min Act: -0.0000

Data Index: 903945 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.4388. Min Act: -0.0000

Data Index: 190480 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1119110 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1099436 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1329893 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1153311 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.3987. Min Act: -0.0000

Data Index: 21357 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1161615 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.4092. Min Act: -0.0000

Data Index: 24878 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.3806. Min Act: -0.0000

Data Index: 729761 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.4205. Min Act: -0.0000

Data Index: 344427 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.3904. Min Act: -0.0000

Data Index: 331603 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.3708. Min Act: -0.0000

Data Index: 508313 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.3423. Min Act: -0.0000

Data Index: 579942 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.5336. Min Range: -0.5336

Max Act: 0.3929. Min Act: -0.0000

Data Index: 913380 (C4 (Web Text))

Max Activating Token Index: 705