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

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

Neuron 3155 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1384090 (Python Code)

Max Activating Token Index: 963

Text #1

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1481325 (Python Code)

Max Activating Token Index: 800

Text #2

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1521610 (Python Code)

Max Activating Token Index: 286

Text #3

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1613388 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1467256 (Python Code)

Max Activating Token Index: 224

Text #5

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1538792 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1654021 (Python Code)

Max Activating Token Index: 535

Text #7

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1377577 (Python Code)

Max Activating Token Index: 322

Text #8

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9578. Min Act: -0.0000

Data Index: 1535658 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1519763 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1475389 (Python Code)

Max Activating Token Index: 258

Text #11

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1477997 (Python Code)

Max Activating Token Index: 232

Text #12

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1628633 (Python Code)

Max Activating Token Index: 383

Text #13

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1267488 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1407441 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1434692 (Python Code)

Max Activating Token Index: 311

Text #16

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1581694 (Python Code)

Max Activating Token Index: 133

Text #17

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1399677 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.8223. Min Act: -0.0000

Data Index: 867514 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1388818 (Python Code)

Max Activating Token Index: 213