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

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

Neuron 4096 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6846. Min Range: -2.6846

Max Act: 2.6846. Min Act: -0.0000

Data Index: 1533663 (Python Code)

Max Activating Token Index: 937

Text #1

Max Range: 2.6846. Min Range: -2.6846

Max Act: 2.6830. Min Act: -0.0000

Data Index: 1374475 (Python Code)

Max Activating Token Index: 704

Text #2

Max Range: 2.6846. Min Range: -2.6846

Max Act: 2.5840. Min Act: -0.0000

Data Index: 1652453 (Python Code)

Max Activating Token Index: 567

Text #3

Max Range: 2.6846. Min Range: -2.6846

Max Act: 2.5064. Min Act: -0.0000

Data Index: 1519565 (Python Code)

Max Activating Token Index: 914

Text #4

Max Range: 2.6846. Min Range: -2.6846

Max Act: 2.4713. Min Act: -0.0000

Data Index: 1537030 (Python Code)

Max Activating Token Index: 435

Text #5

Max Range: 2.6846. Min Range: -2.6846

Max Act: 2.2615. Min Act: -0.0000

Data Index: 1476414 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 2.6846. Min Range: -2.6846

Max Act: 2.3029. Min Act: -0.0000

Data Index: 1384607 (Python Code)

Max Activating Token Index: 290

Text #7

Max Range: 2.6846. Min Range: -2.6846

Max Act: 2.2138. Min Act: -0.0000

Data Index: 1590380 (Python Code)

Max Activating Token Index: 561

Text #8

Max Range: 2.6846. Min Range: -2.6846

Max Act: 2.1239. Min Act: -0.0000

Data Index: 1512882 (Python Code)

Max Activating Token Index: 707

Text #9

Max Range: 2.6846. Min Range: -2.6846

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1452691 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 2.6846. Min Range: -2.6846

Max Act: 1.9433. Min Act: -0.0000

Data Index: 1626656 (Python Code)

Max Activating Token Index: 453

Text #11

Max Range: 2.6846. Min Range: -2.6846

Max Act: 2.0128. Min Act: -0.0000

Data Index: 1377995 (Python Code)

Max Activating Token Index: 712

Text #12

Max Range: 2.6846. Min Range: -2.6846

Max Act: 1.8867. Min Act: -0.0000

Data Index: 1411995 (Python Code)

Max Activating Token Index: 468

Text #13

Max Range: 2.6846. Min Range: -2.6846

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1548159 (Python Code)

Max Activating Token Index: 899

Text #14

Max Range: 2.6846. Min Range: -2.6846

Max Act: 1.9404. Min Act: -0.0000

Data Index: 1524583 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 2.6846. Min Range: -2.6846

Max Act: 1.7720. Min Act: -0.0000

Data Index: 1553675 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 2.6846. Min Range: -2.6846

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1627400 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 2.6846. Min Range: -2.6846

Max Act: 1.7137. Min Act: -0.0000

Data Index: 1137282 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 2.6846. Min Range: -2.6846

Max Act: 1.7196. Min Act: -0.0000

Data Index: 1646898 (Python Code)

Max Activating Token Index: 660

Text #19

Max Range: 2.6846. Min Range: -2.6846

Max Act: 1.5771. Min Act: -0.0000

Data Index: 1619569 (Python Code)

Max Activating Token Index: 1010