Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 601 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.1204. Min Range: -4.1204

Max Act: 4.1204. Min Act: -0.1700

Data Index: 1515787 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 4.1204. Min Range: -4.1204

Max Act: 4.0266. Min Act: -0.1700

Data Index: 1471325 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.9328. Min Act: -0.1700

Data Index: 1655364 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.9641. Min Act: -0.1700

Data Index: 1427504 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.9641. Min Act: -0.1700

Data Index: 1433974 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.8703. Min Act: -0.1700

Data Index: 1512982 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.8390. Min Act: -0.1700

Data Index: 1395545 (Python Code)

Max Activating Token Index: 97

Text #7

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.7764. Min Act: -0.1700

Data Index: 1534209 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.7451. Min Act: -0.1700

Data Index: 1449449 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.7451. Min Act: -0.1700

Data Index: 1584028 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.6825. Min Act: -0.1700

Data Index: 1422096 (Python Code)

Max Activating Token Index: 757

Text #11

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.7138. Min Act: -0.1700

Data Index: 1614259 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.6825. Min Act: -0.1700

Data Index: 1638832 (Python Code)

Max Activating Token Index: 65

Text #13

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.6825. Min Act: -0.1700

Data Index: 1486124 (Python Code)

Max Activating Token Index: 25

Text #14

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.7138. Min Act: -0.1700

Data Index: 1406776 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.6825. Min Act: -0.1700

Data Index: 1542567 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.6825. Min Act: -0.1700

Data Index: 1442819 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.5886. Min Act: -0.1700

Data Index: 1652260 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.6199. Min Act: -0.1700

Data Index: 1392149 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 4.1204. Min Range: -4.1204

Max Act: 3.5886. Min Act: -0.1700

Data Index: 1425744 (Python Code)

Max Activating Token Index: 311