Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 999 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.7372. Min Act: -0.1700

Data Index: 1656800 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.6604. Min Act: -0.1700

Data Index: 1481975 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.6371. Min Act: -0.1700

Data Index: 1543334 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.6053. Min Act: -0.1700

Data Index: 1412781 (Python Code)

Max Activating Token Index: 18

Text #4

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.5920. Min Act: -0.1700

Data Index: 1569753 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.4817. Min Act: -0.1700

Data Index: 1450436 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.4495. Min Act: -0.1700

Data Index: 1524078 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.4645. Min Act: -0.1700

Data Index: 1425545 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.4114. Min Act: -0.1700

Data Index: 1370502 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.4172. Min Act: -0.1700

Data Index: 1373742 (Python Code)

Max Activating Token Index: 782

Text #10

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.3875. Min Act: -0.1700

Data Index: 1567671 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.4180. Min Act: -0.1700

Data Index: 1467112 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.3722. Min Act: -0.1700

Data Index: 1451762 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.4016. Min Act: -0.1700

Data Index: 1644730 (Python Code)

Max Activating Token Index: 992

Text #14

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.3968. Min Act: -0.1700

Data Index: 1574510 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.3554. Min Act: -0.1700

Data Index: 1494101 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.3737. Min Act: -0.1700

Data Index: 1427264 (Python Code)

Max Activating Token Index: 850

Text #17

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.3795. Min Act: -0.1700

Data Index: 1391345 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.3870. Min Act: -0.1700

Data Index: 1556550 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 4.7372. Min Range: -4.7372

Max Act: 4.3606. Min Act: -0.1700

Data Index: 1416405 (Python Code)

Max Activating Token Index: 384