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

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

Neuron 5852 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.3735. Min Act: -0.0000

Data Index: 1404370 (Python Code)

Max Activating Token Index: 245

Text #1

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4850. Min Act: -0.0001

Data Index: 1442580 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4153. Min Act: -0.0001

Data Index: 1457929 (Python Code)

Max Activating Token Index: 950

Text #3

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.3910. Min Act: -0.0000

Data Index: 1400611 (Python Code)

Max Activating Token Index: 387

Text #4

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.6740. Min Act: -0.0000

Data Index: 1453751 (Python Code)

Max Activating Token Index: 666

Text #5

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4658. Min Act: -0.0000

Data Index: 1496281 (Python Code)

Max Activating Token Index: 934

Text #6

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2997. Min Act: -0.0000

Data Index: 1566060 (Python Code)

Max Activating Token Index: 349

Text #7

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2826. Min Act: -0.0001

Data Index: 1550295 (Python Code)

Max Activating Token Index: 449

Text #8

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2524. Min Act: -0.0001

Data Index: 1615466 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.1498. Min Act: -0.0000

Data Index: 1554386 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 3.6740. Min Range: -3.6740

Max Act: 2.9671. Min Act: -0.0000

Data Index: 1561908 (Python Code)

Max Activating Token Index: 161

Text #11

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2222. Min Act: -0.0001

Data Index: 1581070 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2216. Min Act: -0.0000

Data Index: 1377816 (Python Code)

Max Activating Token Index: 448

Text #13

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2266. Min Act: -0.0001

Data Index: 1440486 (Python Code)

Max Activating Token Index: 858

Text #14

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2008. Min Act: -0.0000

Data Index: 1500620 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 3.6740. Min Range: -3.6740

Max Act: 2.8685. Min Act: -0.0000

Data Index: 1525506 (Python Code)

Max Activating Token Index: 365

Text #16

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2699. Min Act: -0.0001

Data Index: 1525471 (Python Code)

Max Activating Token Index: 941

Text #17

Max Range: 3.6740. Min Range: -3.6740

Max Act: 2.9808. Min Act: -0.0000

Data Index: 1408843 (Python Code)

Max Activating Token Index: 418

Text #18

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.1040. Min Act: -0.0001

Data Index: 1410092 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 3.6740. Min Range: -3.6740

Max Act: 2.8023. Min Act: -0.0000

Data Index: 1366989 (Python Code)

Max Activating Token Index: 167