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

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

Neuron 1187 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.9357. Min Act: -0.0000

Data Index: 1053483 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.6368. Min Act: -0.0000

Data Index: 270802 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.6260. Min Act: -0.0000

Data Index: 1206722 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.6517. Min Act: -0.0000

Data Index: 216114 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.6134. Min Act: -0.0000

Data Index: 71688 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.4455. Min Act: -0.0000

Data Index: 1540263 (Python Code)

Max Activating Token Index: 77

Text #6

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.5147. Min Act: -0.0000

Data Index: 1170051 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.4647. Min Act: -0.0000

Data Index: 1541700 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.5013. Min Act: -0.0000

Data Index: 1407475 (Python Code)

Max Activating Token Index: 807

Text #9

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.4756. Min Act: -0.0000

Data Index: 582387 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.5756. Min Act: -0.0000

Data Index: 1624791 (Python Code)

Max Activating Token Index: 593

Text #11

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.3901. Min Act: -0.0000

Data Index: 1340134 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.3213. Min Act: -0.0000

Data Index: 1618735 (Python Code)

Max Activating Token Index: 691

Text #13

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.5220. Min Act: -0.0000

Data Index: 545505 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.4186. Min Act: -0.0000

Data Index: 1646477 (Python Code)

Max Activating Token Index: 987

Text #15

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1453851 (Python Code)

Max Activating Token Index: 787

Text #16

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.3938. Min Act: -0.0000

Data Index: 1444819 (Python Code)

Max Activating Token Index: 632

Text #17

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1390199 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1500645 (Python Code)

Max Activating Token Index: 532

Text #19

Max Range: 1.9357. Min Range: -1.9357

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1384123 (Python Code)

Max Activating Token Index: 777