Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5320 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3187. Min Range: -7.3187
Max Act: 7.3187. Min Act: -0.1700
Data Index: 4206125 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3187. Min Range: -7.3187
Max Act: 7.1625. Min Act: -0.1700
Data Index: 4116421 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3187. Min Range: -7.3187
Max Act: 7.0375. Min Act: -0.1700
Data Index: 2014642 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3187. Min Range: -7.3187
Max Act: 7.0375. Min Act: -0.1700
Data Index: 6941878 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.8812. Min Act: -0.1700
Data Index: 7372553 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.8812. Min Act: -0.1700
Data Index: 3235016 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.8500. Min Act: -0.1700
Data Index: 6004329 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.7875. Min Act: -0.1700
Data Index: 718436 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.7562. Min Act: -0.1700
Data Index: 1767352 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.6937. Min Act: -0.1700
Data Index: 8345982 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.6625. Min Act: -0.1700
Data Index: 4754873 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.6625. Min Act: -0.1700
Data Index: 7567356 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.6312. Min Act: -0.1700
Data Index: 2889634 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.6000. Min Act: -0.1700
Data Index: 3670738 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.5687. Min Act: -0.1700
Data Index: 4240778 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.5687. Min Act: -0.1700
Data Index: 5659597 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.5375. Min Act: -0.1700
Data Index: 5428122 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.5062. Min Act: -0.1700
Data Index: 3542906 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.5062. Min Act: -0.1700
Data Index: 5273532 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3187. Min Range: -7.3187
Max Act: 6.5062. Min Act: -0.1700
Data Index: 3133238 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19