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

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

Neuron 3232 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2230. Min Range: -1.2230

Max Act: 1.2230. Min Act: -0.0001

Data Index: 1630982 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.8698. Min Act: -0.0001

Data Index: 1645670 (Python Code)

Max Activating Token Index: 480

Text #2

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.8596. Min Act: -0.0001

Data Index: 1635847 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7687. Min Act: -0.0001

Data Index: 1526455 (Python Code)

Max Activating Token Index: 500

Text #4

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7721. Min Act: -0.0001

Data Index: 1557200 (Python Code)

Max Activating Token Index: 998

Text #5

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.8760. Min Act: -0.0001

Data Index: 1510259 (Python Code)

Max Activating Token Index: 1002

Text #6

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.8393. Min Act: -0.0001

Data Index: 1444244 (Python Code)

Max Activating Token Index: 415

Text #7

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7847. Min Act: -0.0001

Data Index: 1373866 (Python Code)

Max Activating Token Index: 621

Text #8

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.8210. Min Act: -0.0001

Data Index: 1535354 (Python Code)

Max Activating Token Index: 311

Text #9

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7834. Min Act: -0.0001

Data Index: 1476674 (Python Code)

Max Activating Token Index: 780

Text #10

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.6646. Min Act: -0.0001

Data Index: 1379014 (Python Code)

Max Activating Token Index: 773

Text #11

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1519770 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7173. Min Act: -0.0001

Data Index: 1604861 (Python Code)

Max Activating Token Index: 339

Text #13

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.6894. Min Act: -0.0001

Data Index: 1459673 (Python Code)

Max Activating Token Index: 125

Text #14

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7637. Min Act: -0.0001

Data Index: 1492586 (Python Code)

Max Activating Token Index: 487

Text #15

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1405096 (Python Code)

Max Activating Token Index: 714

Text #16

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7201. Min Act: -0.0001

Data Index: 1550116 (Python Code)

Max Activating Token Index: 417

Text #17

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7404. Min Act: -0.0001

Data Index: 1460179 (Python Code)

Max Activating Token Index: 959

Text #18

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.7369. Min Act: -0.0001

Data Index: 1611746 (Python Code)

Max Activating Token Index: 512

Text #19

Max Range: 1.2230. Min Range: -1.2230

Max Act: 0.6028. Min Act: -0.0001

Data Index: 1643984 (Python Code)

Max Activating Token Index: 138