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

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

Neuron 2308 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.2040. Min Act: -0.0001

Data Index: 1570872 (Python Code)

Max Activating Token Index: 847

Text #1

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.1261. Min Act: -0.0001

Data Index: 1519930 (Python Code)

Max Activating Token Index: 900

Text #2

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.1155. Min Act: -0.0001

Data Index: 1458189 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.0581. Min Act: -0.0001

Data Index: 1410827 (Python Code)

Max Activating Token Index: 460

Text #4

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.0847. Min Act: -0.0001

Data Index: 1413597 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.0271. Min Act: -0.0001

Data Index: 1605768 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.0732. Min Act: -0.0001

Data Index: 1652074 (Python Code)

Max Activating Token Index: 819

Text #7

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.0129. Min Act: -0.0001

Data Index: 1401451 (Python Code)

Max Activating Token Index: 447

Text #8

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.0485. Min Act: -0.0001

Data Index: 1528770 (Python Code)

Max Activating Token Index: 357

Text #9

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.0451. Min Act: -0.0001

Data Index: 1404063 (Python Code)

Max Activating Token Index: 831

Text #10

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.0618. Min Act: -0.0001

Data Index: 1584213 (Python Code)

Max Activating Token Index: 354

Text #11

Max Range: 1.2040. Min Range: -1.2040

Max Act: 1.0040. Min Act: -0.0001

Data Index: 1374498 (Python Code)

Max Activating Token Index: 590

Text #12

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.9357. Min Act: -0.0001

Data Index: 1371391 (Python Code)

Max Activating Token Index: 442

Text #13

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8465. Min Act: -0.0001

Data Index: 1442111 (Python Code)

Max Activating Token Index: 801

Text #14

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.9657. Min Act: -0.0001

Data Index: 1649029 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8942. Min Act: -0.0001

Data Index: 1555664 (Python Code)

Max Activating Token Index: 345

Text #16

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8366. Min Act: -0.0001

Data Index: 1651729 (Python Code)

Max Activating Token Index: 362

Text #17

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8867. Min Act: -0.0001

Data Index: 1617271 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1650503 (Python Code)

Max Activating Token Index: 361

Text #19

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8453. Min Act: -0.0001

Data Index: 1481787 (Python Code)

Max Activating Token Index: 39