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

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

Neuron 2846 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1631893 (Python Code)

Max Activating Token Index: 231

Text #1

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1442964 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1490673 (Python Code)

Max Activating Token Index: 495

Text #3

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1528711 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7107. Min Act: -0.0000

Data Index: 1582344 (Python Code)

Max Activating Token Index: 976

Text #5

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1400406 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1598947 (Python Code)

Max Activating Token Index: 595

Text #7

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1488467 (Python Code)

Max Activating Token Index: 441

Text #8

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1646616 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1475109 (Python Code)

Max Activating Token Index: 186

Text #10

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1533343 (Python Code)

Max Activating Token Index: 633

Text #11

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1623532 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1589327 (Python Code)

Max Activating Token Index: 585

Text #13

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1622399 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1402676 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1606590 (Python Code)

Max Activating Token Index: 88

Text #16

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1605060 (Python Code)

Max Activating Token Index: 319

Text #17

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1478870 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5283. Min Act: -0.0000

Data Index: 1595529 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1503017 (Python Code)

Max Activating Token Index: 154