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

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

Neuron 5431 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7825. Min Range: -2.7825

Max Act: 2.7825. Min Act: -0.0000

Data Index: 1451173 (Python Code)

Max Activating Token Index: 542

Text #1

Max Range: 2.7825. Min Range: -2.7825

Max Act: 2.2781. Min Act: -0.0000

Data Index: 1501627 (Python Code)

Max Activating Token Index: 484

Text #2

Max Range: 2.7825. Min Range: -2.7825

Max Act: 2.2203. Min Act: -0.0000

Data Index: 1615186 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.9371. Min Act: -0.0000

Data Index: 1425970 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 2.7825. Min Range: -2.7825

Max Act: 2.1619. Min Act: -0.0000

Data Index: 1608849 (Python Code)

Max Activating Token Index: 335

Text #5

Max Range: 2.7825. Min Range: -2.7825

Max Act: 2.0308. Min Act: -0.0000

Data Index: 1613556 (Python Code)

Max Activating Token Index: 541

Text #6

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.8795. Min Act: -0.0000

Data Index: 1415918 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.8791. Min Act: -0.0000

Data Index: 1445649 (Python Code)

Max Activating Token Index: 870

Text #8

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.7657. Min Act: -0.0000

Data Index: 1556638 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.8578. Min Act: -0.0000

Data Index: 1594920 (Python Code)

Max Activating Token Index: 734

Text #10

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.6902. Min Act: -0.0000

Data Index: 1609352 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.7815. Min Act: -0.0000

Data Index: 1465006 (Python Code)

Max Activating Token Index: 663

Text #12

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.5889. Min Act: -0.0000

Data Index: 1649759 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.7717. Min Act: -0.0000

Data Index: 1571475 (Python Code)

Max Activating Token Index: 554

Text #14

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.7584. Min Act: -0.0000

Data Index: 1453603 (Python Code)

Max Activating Token Index: 870

Text #15

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.7561. Min Act: -0.0000

Data Index: 1611062 (Python Code)

Max Activating Token Index: 620

Text #16

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.7325. Min Act: -0.0000

Data Index: 1576240 (Python Code)

Max Activating Token Index: 282

Text #17

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.6939. Min Act: -0.0000

Data Index: 1365118 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.5792. Min Act: -0.0000

Data Index: 1511945 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 2.7825. Min Range: -2.7825

Max Act: 1.6788. Min Act: -0.0000

Data Index: 1643290 (Python Code)

Max Activating Token Index: 535