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

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

Neuron 2467 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: 0.6338. Min Range: -0.6338

Max Act: 0.6177. Min Act: 0.0000

Data Index: 850775 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5671. Min Act: -0.0000

Data Index: 809703 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5672. Min Act: 0.0001

Data Index: 165340 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1281649 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5206. Min Act: 0.0000

Data Index: 893889 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1261931 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4643. Min Act: 0.0000

Data Index: 739614 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1140946 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4370. Min Act: -0.0000

Data Index: 593146 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4863. Min Act: 0.0001

Data Index: 930285 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4812. Min Act: 0.0000

Data Index: 731525 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4773. Min Act: -0.0000

Data Index: 972093 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1059043 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4072. Min Act: -0.0000

Data Index: 342392 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4629. Min Act: 0.0000

Data Index: 754703 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1139144 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4688. Min Act: 0.0001

Data Index: 16496 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4738. Min Act: 0.0000

Data Index: 312818 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4128. Min Act: -0.0000

Data Index: 218618 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4251. Min Act: -0.0000

Data Index: 945494 (C4 (Web Text))

Max Activating Token Index: 703