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

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

Neuron 5696 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2729. Min Range: -2.2729

Max Act: 2.2729. Min Act: -0.0000

Data Index: 1422731 (Python Code)

Max Activating Token Index: 437

Text #1

Max Range: 2.2729. Min Range: -2.2729

Max Act: 2.1215. Min Act: -0.0000

Data Index: 1593700 (Python Code)

Max Activating Token Index: 943

Text #2

Max Range: 2.2729. Min Range: -2.2729

Max Act: 2.2248. Min Act: -0.0000

Data Index: 1465134 (Python Code)

Max Activating Token Index: 217

Text #3

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.9649. Min Act: -0.0000

Data Index: 1470646 (Python Code)

Max Activating Token Index: 1003

Text #4

Max Range: 2.2729. Min Range: -2.2729

Max Act: 2.0621. Min Act: -0.0000

Data Index: 1523595 (Python Code)

Max Activating Token Index: 19

Text #5

Max Range: 2.2729. Min Range: -2.2729

Max Act: 2.0347. Min Act: -0.0000

Data Index: 1570765 (Python Code)

Max Activating Token Index: 562

Text #6

Max Range: 2.2729. Min Range: -2.2729

Max Act: 2.0279. Min Act: -0.0000

Data Index: 1556787 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.8998. Min Act: -0.0000

Data Index: 1561755 (Python Code)

Max Activating Token Index: 805

Text #8

Max Range: 2.2729. Min Range: -2.2729

Max Act: 2.0156. Min Act: -0.0000

Data Index: 1490577 (Python Code)

Max Activating Token Index: 919

Text #9

Max Range: 2.2729. Min Range: -2.2729

Max Act: 2.0117. Min Act: -0.0000

Data Index: 1399205 (Python Code)

Max Activating Token Index: 895

Text #10

Max Range: 2.2729. Min Range: -2.2729

Max Act: 2.0045. Min Act: -0.0000

Data Index: 1621279 (Python Code)

Max Activating Token Index: 855

Text #11

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.8630. Min Act: -0.0000

Data Index: 1656901 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.9879. Min Act: -0.0000

Data Index: 1369444 (Python Code)

Max Activating Token Index: 210

Text #13

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.9507. Min Act: -0.0000

Data Index: 1619072 (Python Code)

Max Activating Token Index: 248

Text #14

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.8507. Min Act: -0.0000

Data Index: 1372153 (Python Code)

Max Activating Token Index: 377

Text #15

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.8101. Min Act: -0.0000

Data Index: 1584594 (Python Code)

Max Activating Token Index: 819

Text #16

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1541172 (Python Code)

Max Activating Token Index: 316

Text #17

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.9843. Min Act: -0.0000

Data Index: 1614698 (Python Code)

Max Activating Token Index: 242

Text #18

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.8698. Min Act: -0.0000

Data Index: 1548970 (Python Code)

Max Activating Token Index: 94

Text #19

Max Range: 2.2729. Min Range: -2.2729

Max Act: 1.9099. Min Act: -0.0000

Data Index: 1571176 (Python Code)

Max Activating Token Index: 849