Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3244 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.8144. Min Act: -0.1700
Data Index: 2541854 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.6894. Min Act: -0.1700
Data Index: 3445545 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.5644. Min Act: -0.1700
Data Index: 2557163 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.5644. Min Act: -0.1700
Data Index: 1663605 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.5644. Min Act: -0.1700
Data Index: 4607456 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.5644. Min Act: -0.1700
Data Index: 6146164 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.5644. Min Act: -0.1700
Data Index: 1206638 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.5019. Min Act: -0.1700
Data Index: 4318805 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.4394. Min Act: -0.1700
Data Index: 4607453 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.4394. Min Act: -0.1700
Data Index: 6793061 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.3144. Min Act: -0.1700
Data Index: 8446777 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.2519. Min Act: -0.1700
Data Index: 8620647 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.3144. Min Act: -0.1700
Data Index: 1206633 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.2519. Min Act: -0.1700
Data Index: 1668565 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.3144. Min Act: -0.1700
Data Index: 1931717 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.3144. Min Act: -0.1700
Data Index: 8390354 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.3144. Min Act: -0.1700
Data Index: 5989922 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.3144. Min Act: -0.1698
Data Index: 7282370 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.3144. Min Act: -0.1700
Data Index: 6807168 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8144. Min Range: -8.8144
Max Act: 8.2519. Min Act: -0.1700
Data Index: 1206639 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19