Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1007. Min Range: -7.1007
Max Act: 7.1007. Min Act: -0.1700
Data Index: 7436240 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1007. Min Range: -7.1007
Max Act: 7.1007. Min Act: -0.1700
Data Index: 8134313 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1007. Min Range: -7.1007
Max Act: 7.1007. Min Act: -0.1700
Data Index: 8375114 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1007. Min Range: -7.1007
Max Act: 7.1007. Min Act: -0.1700
Data Index: 1875571 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1007. Min Range: -7.1007
Max Act: 7.0382. Min Act: -0.1700
Data Index: 6763159 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1007. Min Range: -7.1007
Max Act: 7.0382. Min Act: -0.1700
Data Index: 7808549 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1007. Min Range: -7.1007
Max Act: 7.0382. Min Act: -0.1700
Data Index: 8490234 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1007. Min Range: -7.1007
Max Act: 7.0382. Min Act: -0.1700
Data Index: 5901692 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1007. Min Range: -7.1007
Max Act: 7.0382. Min Act: -0.1700
Data Index: 5623339 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1697
Data Index: 5831988 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1700
Data Index: 2099233 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1700
Data Index: 2035299 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1700
Data Index: 5733083 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1700
Data Index: 5685101 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1700
Data Index: 5459733 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1700
Data Index: 1689576 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1700
Data Index: 4910854 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1700
Data Index: 4724271 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1700
Data Index: 3838617 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1007. Min Range: -7.1007
Max Act: 6.9757. Min Act: -0.1700
Data Index: 375440 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19