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

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

Neuron 1385 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: 3.7521. Min Range: -3.7521

Max Act: 3.7521. Min Act: -0.1700

Data Index: 964749 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.7280. Min Act: -0.1700

Data Index: 1641901 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6878. Min Act: -0.1700

Data Index: 1490239 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6770. Min Act: -0.1700

Data Index: 1459578 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6648. Min Act: -0.1700

Data Index: 1362343 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6265. Min Act: -0.1700

Data Index: 1575918 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6462. Min Act: -0.1700

Data Index: 1598280 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6121. Min Act: -0.1700

Data Index: 1517396 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6145. Min Act: -0.1700

Data Index: 1609066 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5755. Min Act: -0.1700

Data Index: 1453084 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5149. Min Act: -0.1700

Data Index: 1585692 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5378. Min Act: -0.1700

Data Index: 1628037 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5179. Min Act: -0.1700

Data Index: 1509578 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5004. Min Act: -0.1700

Data Index: 1617821 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4749. Min Act: -0.1700

Data Index: 1599510 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4736. Min Act: -0.1700

Data Index: 1533211 (Python Code)

Max Activating Token Index: 141

Text #16

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4071. Min Act: -0.1700

Data Index: 1370001 (Python Code)

Max Activating Token Index: 227

Text #17

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4148. Min Act: -0.1700

Data Index: 1592273 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4131. Min Act: -0.1700

Data Index: 1558102 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4104. Min Act: -0.1700

Data Index: 1639929 (Python Code)

Max Activating Token Index: 247