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

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

Neuron 4179 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7093. Min Range: -3.7093

Max Act: 3.7093. Min Act: -0.0000

Data Index: 1468673 (Python Code)

Max Activating Token Index: 779

Text #1

Max Range: 3.7093. Min Range: -3.7093

Max Act: 3.3654. Min Act: -0.0000

Data Index: 1467032 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 3.7093. Min Range: -3.7093

Max Act: 3.0017. Min Act: -0.0000

Data Index: 1405253 (Python Code)

Max Activating Token Index: 489

Text #3

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.6322. Min Act: -0.0000

Data Index: 1469320 (Python Code)

Max Activating Token Index: 254

Text #4

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.7960. Min Act: -0.0000

Data Index: 1589423 (Python Code)

Max Activating Token Index: 533

Text #5

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.5995. Min Act: -0.0000

Data Index: 1451064 (Python Code)

Max Activating Token Index: 740

Text #6

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.9294. Min Act: -0.0000

Data Index: 1570582 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.0939. Min Act: -0.0000

Data Index: 1562042 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.6028. Min Act: -0.0000

Data Index: 1415560 (Python Code)

Max Activating Token Index: 454

Text #9

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.7128. Min Act: -0.0000

Data Index: 1457884 (Python Code)

Max Activating Token Index: 487

Text #10

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.5670. Min Act: -0.0000

Data Index: 1581415 (Python Code)

Max Activating Token Index: 341

Text #11

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.1794. Min Act: -0.0000

Data Index: 1493890 (Python Code)

Max Activating Token Index: 764

Text #12

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.5288. Min Act: -0.0000

Data Index: 1391489 (Python Code)

Max Activating Token Index: 974

Text #13

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.5145. Min Act: -0.0000

Data Index: 1482242 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.3336. Min Act: -0.0000

Data Index: 1592257 (Python Code)

Max Activating Token Index: 498

Text #15

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.2181. Min Act: -0.0000

Data Index: 1442279 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.0955. Min Act: -0.0000

Data Index: 1462471 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.1901. Min Act: -0.0000

Data Index: 1492597 (Python Code)

Max Activating Token Index: 912

Text #18

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.4378. Min Act: -0.0000

Data Index: 1648687 (Python Code)

Max Activating Token Index: 591

Text #19

Max Range: 3.7093. Min Range: -3.7093

Max Act: 2.1658. Min Act: -0.0000

Data Index: 1512596 (Python Code)

Max Activating Token Index: 183