Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1857 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.9125. Min Act: -0.1700
Data Index: 1567064 (Python Code)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.8500. Min Act: -0.1700
Data Index: 1567273 (Python Code)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.8500. Min Act: -0.1700
Data Index: 1549584 (Python Code)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.8187. Min Act: -0.1700
Data Index: 1591095 (Python Code)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.8187. Min Act: -0.1700
Data Index: 1466253 (Python Code)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.8500. Min Act: -0.1700
Data Index: 1651976 (Python Code)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.8500. Min Act: -0.1699
Data Index: 1592673 (Python Code)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.8187. Min Act: -0.1700
Data Index: 1629531 (Python Code)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7561. Min Act: -0.1700
Data Index: 1613661 (Python Code)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7561. Min Act: -0.1700
Data Index: 1518047 (Python Code)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7561. Min Act: -0.1700
Data Index: 1450219 (Python Code)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7248. Min Act: -0.1700
Data Index: 1623215 (Python Code)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7248. Min Act: -0.1700
Data Index: 1391104 (Python Code)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7561. Min Act: -0.1700
Data Index: 1369238 (Python Code)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7561. Min Act: -0.1700
Data Index: 1627637 (Python Code)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7561. Min Act: -0.1700
Data Index: 1552261 (Python Code)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7561. Min Act: -0.1700
Data Index: 1376482 (Python Code)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7874. Min Act: -0.1700
Data Index: 1461614 (Python Code)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7248. Min Act: -0.1700
Data Index: 1514811 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.6622. Min Act: -0.1700
Data Index: 1461504 (Python Code)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19