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

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

Neuron 3188 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.9915. Min Act: -0.0000

Data Index: 1433884 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.9986. Min Act: -0.0000

Data Index: 1513400 (Python Code)

Max Activating Token Index: 898

Text #2

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.7313. Min Act: -0.0000

Data Index: 811213 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.6885. Min Act: -0.0000

Data Index: 1498823 (Python Code)

Max Activating Token Index: 582

Text #4

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.8394. Min Act: -0.0000

Data Index: 207737 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.7084. Min Act: -0.0000

Data Index: 1472087 (Python Code)

Max Activating Token Index: 806

Text #6

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.6150. Min Act: -0.0000

Data Index: 475655 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.4887. Min Act: -0.0000

Data Index: 1202553 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.6720. Min Act: -0.0000

Data Index: 1376946 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.6184. Min Act: -0.0000

Data Index: 157731 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.5162. Min Act: -0.0000

Data Index: 1182307 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1047222 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1481734 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.4411. Min Act: -0.0000

Data Index: 1499595 (Python Code)

Max Activating Token Index: 838

Text #14

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1397591 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.3434. Min Act: -0.0000

Data Index: 1526427 (Python Code)

Max Activating Token Index: 547

Text #16

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1628203 (Python Code)

Max Activating Token Index: 742

Text #17

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1548312 (Python Code)

Max Activating Token Index: 321

Text #18

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.3669. Min Act: -0.0000

Data Index: 986720 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.3007. Min Act: -0.0000

Data Index: 1620405 (Python Code)

Max Activating Token Index: 919