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

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

Neuron 4865 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1243707 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.8260. Min Act: -0.0000

Data Index: 338540 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1144371 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7573. Min Act: -0.0000

Data Index: 72252 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1088387 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1275060 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1060185 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6745. Min Act: -0.0000

Data Index: 972558 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7002. Min Act: -0.0000

Data Index: 660126 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5896. Min Act: -0.0000

Data Index: 160923 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1295588 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5509. Min Act: -0.0000

Data Index: 643894 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5731. Min Act: -0.0000

Data Index: 15391 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5065. Min Act: -0.0000

Data Index: 480774 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5848. Min Act: -0.0000

Data Index: 606604 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1144829 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5377. Min Act: -0.0000

Data Index: 30020 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5519. Min Act: -0.0000

Data Index: 491748 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5430. Min Act: -0.0000

Data Index: 10641 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1027304 (C4 (Web Text))

Max Activating Token Index: 784