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

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

Neuron 3183 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1521292 (Python Code)

Max Activating Token Index: 283

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1393909 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1548445 (Python Code)

Max Activating Token Index: 316

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1527111 (Python Code)

Max Activating Token Index: 819

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1410496 (Python Code)

Max Activating Token Index: 289

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1512819 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1463262 (Python Code)

Max Activating Token Index: 137

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1369830 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0294. Min Act: -0.0001

Data Index: 1433684 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1565543 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1475541 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1478377 (Python Code)

Max Activating Token Index: 182

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1651091 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1480152 (Python Code)

Max Activating Token Index: 691

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1508723 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1523470 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1539135 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1577826 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1458747 (Python Code)

Max Activating Token Index: 228

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1542021 (Python Code)

Max Activating Token Index: 24