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

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

Neuron 4915 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4064. Min Range: -3.4064

Max Act: 3.4064. Min Act: 0.0000

Data Index: 1419647 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.6475. Min Act: 0.0001

Data Index: 1625477 (Python Code)

Max Activating Token Index: 629

Text #2

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.7492. Min Act: -0.0000

Data Index: 1628004 (Python Code)

Max Activating Token Index: 310

Text #3

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.6780. Min Act: -0.0000

Data Index: 1482197 (Python Code)

Max Activating Token Index: 731

Text #4

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.6776. Min Act: -0.0000

Data Index: 1600066 (Python Code)

Max Activating Token Index: 804

Text #5

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.6126. Min Act: 0.0001

Data Index: 1499518 (Python Code)

Max Activating Token Index: 994

Text #6

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.4484. Min Act: 0.0000

Data Index: 1436620 (Python Code)

Max Activating Token Index: 893

Text #7

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.5636. Min Act: 0.0001

Data Index: 1513000 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.5430. Min Act: -0.0000

Data Index: 1502259 (Python Code)

Max Activating Token Index: 990

Text #9

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.5434. Min Act: 0.0001

Data Index: 1365860 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.5270. Min Act: -0.0000

Data Index: 1396610 (Python Code)

Max Activating Token Index: 490

Text #11

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.5061. Min Act: 0.0002

Data Index: 1608890 (Python Code)

Max Activating Token Index: 533

Text #12

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.4834. Min Act: 0.0000

Data Index: 1409527 (Python Code)

Max Activating Token Index: 356

Text #13

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.4813. Min Act: -0.0000

Data Index: 1615848 (Python Code)

Max Activating Token Index: 698

Text #14

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.2208. Min Act: -0.0000

Data Index: 1410426 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.7277. Min Act: -0.0000

Data Index: 1403941 (Python Code)

Max Activating Token Index: 648

Text #16

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.5539. Min Act: -0.0000

Data Index: 1571766 (Python Code)

Max Activating Token Index: 917

Text #17

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.2918. Min Act: -0.0000

Data Index: 1418611 (Python Code)

Max Activating Token Index: 335

Text #18

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.5379. Min Act: -0.0000

Data Index: 1654655 (Python Code)

Max Activating Token Index: 433

Text #19

Max Range: 3.4064. Min Range: -3.4064

Max Act: 2.5034. Min Act: -0.0000

Data Index: 1508674 (Python Code)

Max Activating Token Index: 691