Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.9129. Min Act: -0.1700
Data Index: 7145479 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.7566. Min Act: -0.1700
Data Index: 7740115 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.6941. Min Act: -0.1700
Data Index: 8648089 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.6629. Min Act: -0.1700
Data Index: 6952560 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.6629. Min Act: -0.1700
Data Index: 5373265 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.6004. Min Act: -0.1700
Data Index: 6635007 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.4754. Min Act: -0.1700
Data Index: 5523509 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.4754. Min Act: -0.1700
Data Index: 8560718 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.4129. Min Act: -0.1700
Data Index: 7252881 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.4129. Min Act: -0.1700
Data Index: 2366493 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.4129. Min Act: -0.1700
Data Index: 8561510 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.4129. Min Act: -0.1700
Data Index: 4078056 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.3816. Min Act: -0.1700
Data Index: 6894382 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.3816. Min Act: -0.1700
Data Index: 7303962 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.3191. Min Act: -0.1700
Data Index: 7807561 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.2879. Min Act: -0.1700
Data Index: 4436005 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.3504. Min Act: -0.1700
Data Index: 2182732 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.2879. Min Act: -0.1700
Data Index: 5162849 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.2879. Min Act: -0.1700
Data Index: 1273807 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9129. Min Range: -6.9129
Max Act: 6.2566. Min Act: -0.1700
Data Index: 8188833 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19