Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1246 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.5073. Min Act: 0.0001

Data Index: 1582522 (Python Code)

Max Activating Token Index: 698

Text #1

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4701. Min Act: -0.0000

Data Index: 942592 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1505826 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4296. Min Act: 0.0000

Data Index: 1633822 (Python Code)

Max Activating Token Index: 944

Text #4

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1154953 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4570. Min Act: -0.0001

Data Index: 1603974 (Python Code)

Max Activating Token Index: 631

Text #6

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1363476 (Python Code)

Max Activating Token Index: 291

Text #7

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4195. Min Act: -0.0000

Data Index: 783868 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4149. Min Act: -0.0000

Data Index: 679459 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4099. Min Act: -0.0000

Data Index: 397210 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4075. Min Act: -0.0000

Data Index: 31691 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4060. Min Act: -0.0001

Data Index: 748208 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4323. Min Act: 0.0001

Data Index: 1608272 (Python Code)

Max Activating Token Index: 778

Text #13

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1058109 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3903. Min Act: -0.0000

Data Index: 144551 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3910. Min Act: -0.0001

Data Index: 662377 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3807. Min Act: -0.0000

Data Index: 886665 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3809. Min Act: -0.0000

Data Index: 692110 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3909. Min Act: -0.0000

Data Index: 789017 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3943. Min Act: -0.0001

Data Index: 303067 (C4 (Web Text))

Max Activating Token Index: 618