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

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

Neuron 4287 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1452551 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1586577 (Python Code)

Max Activating Token Index: 182

Text #2

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1633087 (Python Code)

Max Activating Token Index: 444

Text #3

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1511123 (Python Code)

Max Activating Token Index: 313

Text #4

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1576899 (Python Code)

Max Activating Token Index: 775

Text #5

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1493304 (Python Code)

Max Activating Token Index: 366

Text #6

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1473289 (Python Code)

Max Activating Token Index: 506

Text #7

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1432062 (Python Code)

Max Activating Token Index: 428

Text #8

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1382616 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3063. Min Act: -0.0000

Data Index: 74177 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1540798 (Python Code)

Max Activating Token Index: 572

Text #11

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1390321 (Python Code)

Max Activating Token Index: 583

Text #12

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1466448 (Python Code)

Max Activating Token Index: 652

Text #13

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1655014 (Python Code)

Max Activating Token Index: 879

Text #14

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1543105 (Python Code)

Max Activating Token Index: 854

Text #15

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1434926 (Python Code)

Max Activating Token Index: 923

Text #16

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1566005 (Python Code)

Max Activating Token Index: 410

Text #17

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1439893 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1507942 (Python Code)

Max Activating Token Index: 431

Text #19

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1454410 (Python Code)

Max Activating Token Index: 559