Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 214 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0385. Min Act: -0.0005

Data Index: 1475352 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0005

Data Index: 1535841 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0005

Data Index: 1518921 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1398463 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0387. Min Act: -0.0005

Data Index: 1455100 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0363. Min Act: -0.0005

Data Index: 1448294 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0364. Min Act: -0.0005

Data Index: 1365297 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0363. Min Act: -0.0005

Data Index: 1427732 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0356. Min Act: -0.0005

Data Index: 1425662 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0351. Min Act: -0.0005

Data Index: 1492818 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0341. Min Act: -0.0005

Data Index: 1379274 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0341. Min Act: -0.0005

Data Index: 1383323 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0341. Min Act: -0.0005

Data Index: 1399103 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0341. Min Act: -0.0005

Data Index: 1576799 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0341. Min Act: -0.0005

Data Index: 1472756 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0341. Min Act: -0.0005

Data Index: 1595309 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1590171 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1529054 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1584780 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0324. Min Act: -0.0005

Data Index: 1569186 (Python Code)

Max Activating Token Index: 12