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

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

Neuron 200 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: 3.8149. Min Range: -3.8149

Max Act: 3.8149. Min Act: -0.1700

Data Index: 1467843 (Python Code)

Max Activating Token Index: 789

Text #1

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.7813. Min Act: -0.1700

Data Index: 1656004 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.7535. Min Act: -0.1700

Data Index: 1496009 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.7566. Min Act: -0.1700

Data Index: 1531842 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.7077. Min Act: -0.1700

Data Index: 1591808 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.7387. Min Act: -0.1700

Data Index: 1533474 (Python Code)

Max Activating Token Index: 561

Text #6

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.6660. Min Act: -0.1700

Data Index: 1475380 (Python Code)

Max Activating Token Index: 899

Text #7

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.7175. Min Act: -0.1700

Data Index: 1482033 (Python Code)

Max Activating Token Index: 101

Text #8

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.6981. Min Act: -0.1700

Data Index: 1447900 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.7184. Min Act: -0.1700

Data Index: 1383726 (Python Code)

Max Activating Token Index: 885

Text #10

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.6868. Min Act: -0.1700

Data Index: 1384427 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.6738. Min Act: -0.1700

Data Index: 1552147 (Python Code)

Max Activating Token Index: 609

Text #12

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.6512. Min Act: -0.1700

Data Index: 1621323 (Python Code)

Max Activating Token Index: 249

Text #13

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.6643. Min Act: -0.1700

Data Index: 1399204 (Python Code)

Max Activating Token Index: 401

Text #14

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.6382. Min Act: -0.1700

Data Index: 1585960 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.6312. Min Act: -0.1700

Data Index: 1388689 (Python Code)

Max Activating Token Index: 151

Text #16

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.6486. Min Act: -0.1700

Data Index: 1476909 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.6173. Min Act: -0.1700

Data Index: 1410784 (Python Code)

Max Activating Token Index: 702

Text #18

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.5983. Min Act: -0.1700

Data Index: 1519264 (Python Code)

Max Activating Token Index: 564

Text #19

Max Range: 3.8149. Min Range: -3.8149

Max Act: 3.5996. Min Act: -0.1700

Data Index: 1626166 (Python Code)

Max Activating Token Index: 680