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

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

Neuron 3654 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: 3.2390. Min Range: -3.2390

Max Act: 3.2390. Min Act: -0.0000

Data Index: 151995 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1698. Min Act: -0.0000

Data Index: 477926 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.9413. Min Act: -0.0000

Data Index: 261770 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.8265. Min Act: -0.0000

Data Index: 1297180 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.9236. Min Act: -0.0000

Data Index: 501574 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.7881. Min Act: -0.0000

Data Index: 826233 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.5814. Min Act: -0.0000

Data Index: 1117664 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.6998. Min Act: -0.0000

Data Index: 993345 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.6895. Min Act: -0.0000

Data Index: 694957 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.6398. Min Act: -0.0000

Data Index: 740507 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.7714. Min Act: -0.0000

Data Index: 856989 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.6828. Min Act: -0.0000

Data Index: 1220550 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.6578. Min Act: -0.0000

Data Index: 1003600 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.5043. Min Act: -0.0000

Data Index: 326544 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.4997. Min Act: -0.0000

Data Index: 909974 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.4854. Min Act: -0.0000

Data Index: 836714 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.4517. Min Act: -0.0000

Data Index: 515987 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.5714. Min Act: -0.0000

Data Index: 290379 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 3.2390. Min Range: -3.2390

Max Act: 1.8890. Min Act: -0.0000

Data Index: 1013950 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 3.2390. Min Range: -3.2390

Max Act: 2.1773. Min Act: -0.0000

Data Index: 1020191 (C4 (Web Text))

Max Activating Token Index: 770