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

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

Neuron 4923 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: 4.3050. Min Range: -4.3050

Max Act: 4.2581. Min Act: -0.0000

Data Index: 1385666 (Python Code)

Max Activating Token Index: 647

Text #1

Max Range: 4.3050. Min Range: -4.3050

Max Act: 4.3050. Min Act: -0.0000

Data Index: 1468225 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 4.3050. Min Range: -4.3050

Max Act: 4.2286. Min Act: -0.0000

Data Index: 1562585 (Python Code)

Max Activating Token Index: 80

Text #3

Max Range: 4.3050. Min Range: -4.3050

Max Act: 4.1374. Min Act: -0.0000

Data Index: 1486432 (Python Code)

Max Activating Token Index: 756

Text #4

Max Range: 4.3050. Min Range: -4.3050

Max Act: 3.9186. Min Act: -0.0000

Data Index: 1498608 (Python Code)

Max Activating Token Index: 454

Text #5

Max Range: 4.3050. Min Range: -4.3050

Max Act: 3.6683. Min Act: -0.0000

Data Index: 1447276 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 4.3050. Min Range: -4.3050

Max Act: 3.5677. Min Act: -0.0000

Data Index: 1453535 (Python Code)

Max Activating Token Index: 519

Text #7

Max Range: 4.3050. Min Range: -4.3050

Max Act: 3.0691. Min Act: -0.0000

Data Index: 1505382 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 4.3050. Min Range: -4.3050

Max Act: 3.0272. Min Act: -0.0000

Data Index: 1499611 (Python Code)

Max Activating Token Index: 393

Text #9

Max Range: 4.3050. Min Range: -4.3050

Max Act: 3.1127. Min Act: -0.0000

Data Index: 1457242 (Python Code)

Max Activating Token Index: 866

Text #10

Max Range: 4.3050. Min Range: -4.3050

Max Act: 3.0049. Min Act: -0.0000

Data Index: 1465294 (Python Code)

Max Activating Token Index: 511

Text #11

Max Range: 4.3050. Min Range: -4.3050

Max Act: 2.9652. Min Act: -0.0000

Data Index: 1498758 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 4.3050. Min Range: -4.3050

Max Act: 2.8593. Min Act: -0.0000

Data Index: 1481865 (Python Code)

Max Activating Token Index: 980

Text #13

Max Range: 4.3050. Min Range: -4.3050

Max Act: 2.8387. Min Act: -0.0000

Data Index: 1500752 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 4.3050. Min Range: -4.3050

Max Act: 2.6146. Min Act: -0.0000

Data Index: 1395673 (Python Code)

Max Activating Token Index: 491

Text #15

Max Range: 4.3050. Min Range: -4.3050

Max Act: 2.7076. Min Act: -0.0000

Data Index: 1628726 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 4.3050. Min Range: -4.3050

Max Act: 2.7155. Min Act: -0.0000

Data Index: 1421490 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 4.3050. Min Range: -4.3050

Max Act: 2.7057. Min Act: -0.0000

Data Index: 1501584 (Python Code)

Max Activating Token Index: 1008

Text #18

Max Range: 4.3050. Min Range: -4.3050

Max Act: 2.5862. Min Act: -0.0000

Data Index: 1530950 (Python Code)

Max Activating Token Index: 760

Text #19

Max Range: 4.3050. Min Range: -4.3050

Max Act: 2.2813. Min Act: -0.0000

Data Index: 1489982 (Python Code)

Max Activating Token Index: 48