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

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

Neuron 3920 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.5859. Min Act: -0.0001

Data Index: 1533095 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.3154. Min Act: -0.0001

Data Index: 1379380 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.3697. Min Act: -0.0001

Data Index: 1537115 (Python Code)

Max Activating Token Index: 178

Text #3

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.3960. Min Act: -0.0001

Data Index: 1396815 (Python Code)

Max Activating Token Index: 466

Text #4

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.4111. Min Act: -0.0001

Data Index: 1423591 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.4111. Min Act: -0.0001

Data Index: 1570903 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.4111. Min Act: -0.0001

Data Index: 1620940 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.3578. Min Act: -0.0001

Data Index: 1430428 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.3723. Min Act: -0.0001

Data Index: 1530576 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2002. Min Act: -0.0001

Data Index: 1430640 (Python Code)

Max Activating Token Index: 196

Text #10

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2430. Min Act: -0.0001

Data Index: 1449600 (Python Code)

Max Activating Token Index: 106

Text #11

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2884. Min Act: -0.0001

Data Index: 1559769 (Python Code)

Max Activating Token Index: 256

Text #12

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2688. Min Act: -0.0001

Data Index: 1463211 (Python Code)

Max Activating Token Index: 320

Text #13

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.4129. Min Act: -0.0001

Data Index: 1415810 (Python Code)

Max Activating Token Index: 316

Text #14

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2432. Min Act: -0.0001

Data Index: 1406694 (Python Code)

Max Activating Token Index: 630

Text #15

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2358. Min Act: -0.0001

Data Index: 1397026 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.3225. Min Act: -0.0001

Data Index: 1490228 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.1201. Min Act: -0.0001

Data Index: 1464453 (Python Code)

Max Activating Token Index: 419

Text #18

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2388. Min Act: -0.0001

Data Index: 1467942 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2055. Min Act: -0.0001

Data Index: 1560648 (Python Code)

Max Activating Token Index: 365