Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 63 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.8952. Min Act: -0.1700
Data Index: 3560728 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.8327. Min Act: -0.1700
Data Index: 7442468 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.8327. Min Act: -0.1700
Data Index: 2266361 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.7702. Min Act: -0.1700
Data Index: 4597362 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.7077. Min Act: -0.1700
Data Index: 7442467 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.6452. Min Act: -0.1700
Data Index: 6734145 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.6452. Min Act: -0.1700
Data Index: 4433339 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.6452. Min Act: -0.1700
Data Index: 3005819 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.6452. Min Act: -0.1700
Data Index: 7607930 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.6452. Min Act: -0.1700
Data Index: 6960171 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.6452. Min Act: -0.1700
Data Index: 4597363 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.5827. Min Act: -0.1700
Data Index: 7199011 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.5827. Min Act: -0.1700
Data Index: 3587769 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.6452. Min Act: -0.1700
Data Index: 5340667 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.5827. Min Act: -0.1700
Data Index: 5340666 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.5827. Min Act: -0.1700
Data Index: 7628185 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.5827. Min Act: -0.1700
Data Index: 4115370 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.5202. Min Act: -0.1700
Data Index: 4115369 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.5202. Min Act: -0.1700
Data Index: 4389616 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8952. Min Range: -12.8952
Max Act: 12.5202. Min Act: -0.1700
Data Index: 3133406 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19