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

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

Neuron 5032 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.9417. Min Act: -0.0000

Data Index: 1412603 (Python Code)

Max Activating Token Index: 484

Text #1

Max Range: 2.0258. Min Range: -2.0258

Max Act: 2.0258. Min Act: -0.0000

Data Index: 1553447 (Python Code)

Max Activating Token Index: 645

Text #2

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.7969. Min Act: -0.0000

Data Index: 1639244 (Python Code)

Max Activating Token Index: 905

Text #3

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6952. Min Act: -0.0000

Data Index: 1564675 (Python Code)

Max Activating Token Index: 407

Text #4

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6553. Min Act: -0.0000

Data Index: 1411344 (Python Code)

Max Activating Token Index: 843

Text #5

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6101. Min Act: -0.0000

Data Index: 1552773 (Python Code)

Max Activating Token Index: 512

Text #6

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.7469. Min Act: -0.0000

Data Index: 1491076 (Python Code)

Max Activating Token Index: 824

Text #7

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6438. Min Act: -0.0000

Data Index: 1540087 (Python Code)

Max Activating Token Index: 313

Text #8

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6050. Min Act: -0.0000

Data Index: 1467691 (Python Code)

Max Activating Token Index: 821

Text #9

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.7939. Min Act: -0.0000

Data Index: 1582006 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6964. Min Act: -0.0000

Data Index: 1541732 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6393. Min Act: -0.0000

Data Index: 1464735 (Python Code)

Max Activating Token Index: 444

Text #12

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6073. Min Act: -0.0000

Data Index: 1631336 (Python Code)

Max Activating Token Index: 678

Text #13

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1478718 (Python Code)

Max Activating Token Index: 410

Text #14

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6234. Min Act: -0.0000

Data Index: 1396591 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6494. Min Act: -0.0000

Data Index: 1546662 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6039. Min Act: -0.0000

Data Index: 1605887 (Python Code)

Max Activating Token Index: 377

Text #17

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6435. Min Act: -0.0000

Data Index: 1552899 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6149. Min Act: -0.0000

Data Index: 1380940 (Python Code)

Max Activating Token Index: 674

Text #19

Max Range: 2.0258. Min Range: -2.0258

Max Act: 1.6555. Min Act: -0.0000

Data Index: 1428929 (Python Code)

Max Activating Token Index: 9