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

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

Neuron 390 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: 1.4895. Min Range: -1.4895

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1517367 (Python Code)

Max Activating Token Index: 464

Text #1

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1407008 (Python Code)

Max Activating Token Index: 505

Text #2

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.3342. Min Act: -0.0000

Data Index: 1544247 (Python Code)

Max Activating Token Index: 763

Text #3

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1579283 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.2407. Min Act: -0.0000

Data Index: 1458809 (Python Code)

Max Activating Token Index: 958

Text #5

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.2092. Min Act: -0.0000

Data Index: 1533479 (Python Code)

Max Activating Token Index: 609

Text #6

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1401730 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.1237. Min Act: -0.0000

Data Index: 800376 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1609000 (Python Code)

Max Activating Token Index: 940

Text #9

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1621053 (Python Code)

Max Activating Token Index: 323

Text #10

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.1018. Min Act: -0.0000

Data Index: 161998 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1504971 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.0965. Min Act: -0.0000

Data Index: 1476172 (Python Code)

Max Activating Token Index: 777

Text #13

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.0212. Min Act: -0.0000

Data Index: 977390 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.1400. Min Act: -0.0000

Data Index: 494179 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1396000 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.0614. Min Act: -0.0000

Data Index: 985489 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.0527. Min Act: -0.0000

Data Index: 391018 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.0376. Min Act: -0.0000

Data Index: 1606156 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 1.4895. Min Range: -1.4895

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1073227 (C4 (Web Text))

Max Activating Token Index: 455