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

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

Neuron 3477 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1619626 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1451244 (Python Code)

Max Activating Token Index: 891

Text #2

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1458324 (Python Code)

Max Activating Token Index: 582

Text #3

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1394430 (Python Code)

Max Activating Token Index: 993

Text #4

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1410018 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1607360 (Python Code)

Max Activating Token Index: 286

Text #6

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1416066 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1502182 (Python Code)

Max Activating Token Index: 637

Text #8

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1613055 (Python Code)

Max Activating Token Index: 610

Text #9

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1558404 (Python Code)

Max Activating Token Index: 58

Text #10

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1416361 (Python Code)

Max Activating Token Index: 1020

Text #11

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1434939 (Python Code)

Max Activating Token Index: 714

Text #12

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1385362 (Python Code)

Max Activating Token Index: 325

Text #13

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1389238 (Python Code)

Max Activating Token Index: 998

Text #14

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1446213 (Python Code)

Max Activating Token Index: 117

Text #15

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1558023 (Python Code)

Max Activating Token Index: 318

Text #16

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1361254 (Python Code)

Max Activating Token Index: 425

Text #17

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1567775 (Python Code)

Max Activating Token Index: 458

Text #18

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1382602 (Python Code)

Max Activating Token Index: 895

Text #19

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1418699 (Python Code)

Max Activating Token Index: 834