Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3635 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2001. Min Range: -1.2001

Max Act: 1.2001. Min Act: -0.0001

Data Index: 1624248 (Python Code)

Max Activating Token Index: 601

Text #1

Max Range: 1.2001. Min Range: -1.2001

Max Act: 1.0408. Min Act: -0.0000

Data Index: 1411597 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1438770 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1565763 (Python Code)

Max Activating Token Index: 768

Text #4

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.9422. Min Act: -0.0001

Data Index: 1475404 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1579412 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8165. Min Act: -0.0001

Data Index: 1619574 (Python Code)

Max Activating Token Index: 266

Text #7

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8142. Min Act: -0.0001

Data Index: 1640671 (Python Code)

Max Activating Token Index: 392

Text #8

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1635889 (Python Code)

Max Activating Token Index: 485

Text #9

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1485638 (Python Code)

Max Activating Token Index: 796

Text #10

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1453490 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1562564 (Python Code)

Max Activating Token Index: 790

Text #12

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7562. Min Act: -0.0001

Data Index: 1582164 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1553374 (Python Code)

Max Activating Token Index: 558

Text #14

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1571134 (Python Code)

Max Activating Token Index: 338

Text #15

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1612356 (Python Code)

Max Activating Token Index: 107

Text #16

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.6978. Min Act: -0.0001

Data Index: 1422976 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7136. Min Act: -0.0001

Data Index: 1621354 (Python Code)

Max Activating Token Index: 378

Text #18

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7332. Min Act: -0.0001

Data Index: 1380992 (Python Code)

Max Activating Token Index: 746

Text #19

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1543770 (Python Code)

Max Activating Token Index: 45