Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1371 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0118. Min Range: -8.0118
Max Act: 8.0118. Min Act: -0.1700
Data Index: 5740686 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.4805. Min Act: -0.1700
Data Index: 5740684 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.4493. Min Act: -0.1700
Data Index: 5740678 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.3868. Min Act: -0.1700
Data Index: 5740679 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.3555. Min Act: -0.1700
Data Index: 4768429 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.3243. Min Act: -0.1700
Data Index: 7269032 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.2930. Min Act: -0.1700
Data Index: 3787973 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.2930. Min Act: -0.1700
Data Index: 5740690 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.2618. Min Act: -0.1700
Data Index: 517356 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.2305. Min Act: -0.1700
Data Index: 5740683 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.2305. Min Act: -0.1700
Data Index: 7836853 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.2305. Min Act: -0.1700
Data Index: 2392781 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.2618. Min Act: -0.1700
Data Index: 5740694 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.1993. Min Act: -0.1700
Data Index: 5083388 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.1368. Min Act: -0.1700
Data Index: 5825199 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.1680. Min Act: -0.1700
Data Index: 4340234 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.1055. Min Act: -0.1700
Data Index: 6089666 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.1055. Min Act: -0.1700
Data Index: 3333204 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.0743. Min Act: -0.1700
Data Index: 860661 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0118. Min Range: -8.0118
Max Act: 7.1055. Min Act: -0.1700
Data Index: 2801580 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19