Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4355 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.7117. Min Act: -0.0000

Data Index: 1518253 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.3733. Min Act: -0.0000

Data Index: 1561937 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1504927 (Python Code)

Max Activating Token Index: 636

Text #3

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.4267. Min Act: -0.0000

Data Index: 1416348 (Python Code)

Max Activating Token Index: 448

Text #4

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.3258. Min Act: -0.0000

Data Index: 1439447 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1441592 (Python Code)

Max Activating Token Index: 561

Text #6

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1384731 (Python Code)

Max Activating Token Index: 116

Text #7

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1636705 (Python Code)

Max Activating Token Index: 104

Text #8

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.2478. Min Act: -0.0000

Data Index: 1625999 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.3183. Min Act: -0.0000

Data Index: 1546109 (Python Code)

Max Activating Token Index: 839

Text #10

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.1981. Min Act: -0.0000

Data Index: 1630667 (Python Code)

Max Activating Token Index: 440

Text #11

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1563361 (Python Code)

Max Activating Token Index: 438

Text #12

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.1342. Min Act: -0.0000

Data Index: 1418480 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 1.7117. Min Range: -1.7117

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1633604 (Python Code)

Max Activating Token Index: 195

Text #14

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1416870 (Python Code)

Max Activating Token Index: 584

Text #15

Max Range: 1.7117. Min Range: -1.7117

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1389424 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1654509 (Python Code)

Max Activating Token Index: 747

Text #17

Max Range: 1.7117. Min Range: -1.7117

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1590171 (Python Code)

Max Activating Token Index: 296

Text #18

Max Range: 1.7117. Min Range: -1.7117

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1443290 (Python Code)

Max Activating Token Index: 935

Text #19

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1557052 (Python Code)

Max Activating Token Index: 301