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

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

Neuron 4340 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1584424 (Python Code)

Max Activating Token Index: 673

Text #1

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1366409 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1471596 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1389157 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1390323 (Python Code)

Max Activating Token Index: 639

Text #5

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1652676 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1466086 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1489966 (Python Code)

Max Activating Token Index: 509

Text #8

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1630689 (Python Code)

Max Activating Token Index: 433

Text #9

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1598137 (Python Code)

Max Activating Token Index: 833

Text #10

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5322. Min Act: -0.0000

Data Index: 318038 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5462. Min Act: -0.0000

Data Index: 303920 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1558661 (Python Code)

Max Activating Token Index: 548

Text #13

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1461273 (Python Code)

Max Activating Token Index: 904

Text #14

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1604393 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1644997 (Python Code)

Max Activating Token Index: 154

Text #16

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1616019 (Python Code)

Max Activating Token Index: 456

Text #17

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1590161 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1365479 (Python Code)

Max Activating Token Index: 671

Text #19

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1608433 (Python Code)

Max Activating Token Index: 51