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

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

Neuron 3961 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: 0.3713. Min Range: -0.3713

Max Act: 0.3713. Min Act: -0.0001

Data Index: 1529905 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3421. Min Act: -0.0001

Data Index: 1475757 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3317. Min Act: -0.0001

Data Index: 1409750 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3292. Min Act: -0.0001

Data Index: 1368593 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3285. Min Act: -0.0001

Data Index: 1653872 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3120. Min Act: -0.0001

Data Index: 1568945 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3087. Min Act: -0.0001

Data Index: 1554924 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1551657 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2744. Min Act: -0.0002

Data Index: 1374103 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2687. Min Act: -0.0001

Data Index: 1565623 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2728. Min Act: -0.0001

Data Index: 1429597 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2589. Min Act: -0.0001

Data Index: 1450906 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2563. Min Act: -0.0001

Data Index: 1646098 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2567. Min Act: -0.0001

Data Index: 1601636 (Python Code)

Max Activating Token Index: 621

Text #14

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2474. Min Act: -0.0001

Data Index: 1598478 (Python Code)

Max Activating Token Index: 207

Text #15

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1586333 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1503338 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1415039 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1373762 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2206. Min Act: -0.0001

Data Index: 1517932 (Python Code)

Max Activating Token Index: 139