Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 965 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.5187. Min Act: -0.1700
Data Index: 5089712 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.4562. Min Act: -0.1700
Data Index: 7808672 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.4250. Min Act: -0.1700
Data Index: 1467747 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.3937. Min Act: -0.1700
Data Index: 3489510 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.3000. Min Act: -0.1700
Data Index: 7543395 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2375. Min Act: -0.1700
Data Index: 1187330 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2687. Min Act: -0.1700
Data Index: 6839622 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2375. Min Act: -0.1700
Data Index: 7624102 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2375. Min Act: -0.1700
Data Index: 7132743 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2375. Min Act: -0.1700
Data Index: 1273447 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1750. Min Act: -0.1700
Data Index: 8175925 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1437. Min Act: -0.1700
Data Index: 4491060 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1437. Min Act: -0.1700
Data Index: 3552504 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1125. Min Act: -0.1700
Data Index: 4438229 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1437. Min Act: -0.1700
Data Index: 1095171 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1125. Min Act: -0.1700
Data Index: 7274463 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1125. Min Act: -0.1700
Data Index: 7253470 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1125. Min Act: -0.1700
Data Index: 2944639 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1437. Min Act: -0.1700
Data Index: 1997990 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1125. Min Act: -0.1700
Data Index: 8019425 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19