Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1059 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3449. Min Act: -0.0001

Data Index: 1526450 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3654. Min Act: -0.0001

Data Index: 1523768 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3509. Min Act: -0.0001

Data Index: 1588517 (Python Code)

Max Activating Token Index: 186

Text #3

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3661. Min Act: -0.0001

Data Index: 1618530 (Python Code)

Max Activating Token Index: 705

Text #4

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3436. Min Act: -0.0001

Data Index: 1396054 (Python Code)

Max Activating Token Index: 497

Text #5

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3551. Min Act: -0.0001

Data Index: 1478018 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3197. Min Act: -0.0001

Data Index: 1602285 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3210. Min Act: -0.0001

Data Index: 1382139 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1522924 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3264. Min Act: -0.0001

Data Index: 1372629 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3274. Min Act: -0.0001

Data Index: 1359976 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3249. Min Act: -0.0001

Data Index: 1530599 (Python Code)

Max Activating Token Index: 483

Text #12

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3225. Min Act: -0.0001

Data Index: 1634060 (Python Code)

Max Activating Token Index: 810

Text #13

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2878. Min Act: -0.0001

Data Index: 1366547 (Python Code)

Max Activating Token Index: 577

Text #14

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2901. Min Act: -0.0001

Data Index: 1379711 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2973. Min Act: -0.0001

Data Index: 1426903 (Python Code)

Max Activating Token Index: 368

Text #16

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3115. Min Act: -0.0001

Data Index: 1449950 (Python Code)

Max Activating Token Index: 628

Text #17

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1604025 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1412009 (Python Code)

Max Activating Token Index: 613

Text #19

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3109. Min Act: -0.0001

Data Index: 1619848 (Python Code)

Max Activating Token Index: 415