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

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

Neuron 5090 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: 1.0915. Min Range: -1.0915

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1587175 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1481138 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 1.0915. Min Range: -1.0915

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1469513 (Python Code)

Max Activating Token Index: 769

Text #3

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1639990 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 1.0915. Min Range: -1.0915

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1577609 (Python Code)

Max Activating Token Index: 555

Text #5

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1634230 (Python Code)

Max Activating Token Index: 946

Text #6

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1574083 (Python Code)

Max Activating Token Index: 878

Text #7

Max Range: 1.0915. Min Range: -1.0915

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1470909 (Python Code)

Max Activating Token Index: 636

Text #8

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1384995 (Python Code)

Max Activating Token Index: 805

Text #9

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1649768 (Python Code)

Max Activating Token Index: 331

Text #10

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1563567 (Python Code)

Max Activating Token Index: 766

Text #11

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1575314 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1563147 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1389248 (Python Code)

Max Activating Token Index: 763

Text #14

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1493642 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1361591 (Python Code)

Max Activating Token Index: 617

Text #16

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1384194 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1512089 (Python Code)

Max Activating Token Index: 312

Text #18

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1413339 (Python Code)

Max Activating Token Index: 568

Text #19

Max Range: 1.0915. Min Range: -1.0915

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1533183 (Python Code)

Max Activating Token Index: 913