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

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

Neuron 2484 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1525459 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1621526 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1401016 (Python Code)

Max Activating Token Index: 492

Text #3

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1383330 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1500971 (Python Code)

Max Activating Token Index: 249

Text #5

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1597453 (Python Code)

Max Activating Token Index: 896

Text #6

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1504248 (Python Code)

Max Activating Token Index: 337

Text #7

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1545027 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1515620 (Python Code)

Max Activating Token Index: 613

Text #9

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1536433 (Python Code)

Max Activating Token Index: 689

Text #10

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1464758 (Python Code)

Max Activating Token Index: 438

Text #11

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1468301 (Python Code)

Max Activating Token Index: 914

Text #12

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1647295 (Python Code)

Max Activating Token Index: 585

Text #13

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1521802 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1501222 (Python Code)

Max Activating Token Index: 583

Text #15

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1487552 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1584781 (Python Code)

Max Activating Token Index: 338

Text #17

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1471761 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1445914 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1399023 (Python Code)

Max Activating Token Index: 100