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

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

Neuron 4632 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1222465 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1063911 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6800. Min Act: -0.0000

Data Index: 240988 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6225. Min Act: -0.0000

Data Index: 370336 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5763. Min Act: 0.0001

Data Index: 1305781 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1176909 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5737. Min Act: -0.0000

Data Index: 336606 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5147. Min Act: 0.0000

Data Index: 105264 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5077. Min Act: 0.0001

Data Index: 275166 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5211. Min Act: -0.0000

Data Index: 816286 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5312. Min Act: -0.0000

Data Index: 536115 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5267. Min Act: -0.0000

Data Index: 303144 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5152. Min Act: -0.0000

Data Index: 209419 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4926. Min Act: -0.0000

Data Index: 828690 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1152784 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4949. Min Act: -0.0000

Data Index: 580350 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5089. Min Act: -0.0000

Data Index: 660721 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5154. Min Act: 0.0000

Data Index: 385720 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1234814 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4781. Min Act: -0.0000

Data Index: 944058 (C4 (Web Text))

Max Activating Token Index: 71