Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1463 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1005. Min Range: -6.1005
Max Act: 6.1005. Min Act: -0.1700
Data Index: 6156592 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1005. Min Range: -6.1005
Max Act: 6.0380. Min Act: -0.1700
Data Index: 7238089 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1005. Min Range: -6.1005
Max Act: 6.0067. Min Act: -0.1700
Data Index: 870725 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9755. Min Act: -0.1700
Data Index: 4943369 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9755. Min Act: -0.1700
Data Index: 8828901 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9442. Min Act: -0.1700
Data Index: 2869266 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9442. Min Act: -0.1700
Data Index: 247541 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 247542 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8817. Min Act: -0.1700
Data Index: 6612558 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8817. Min Act: -0.1700
Data Index: 1502158 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8817. Min Act: -0.1700
Data Index: 8533927 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8505. Min Act: -0.1700
Data Index: 827064 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8192. Min Act: -0.1700
Data Index: 4637713 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8192. Min Act: -0.1700
Data Index: 377481 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8192. Min Act: -0.1700
Data Index: 5628638 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8192. Min Act: -0.1700
Data Index: 2217116 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8192. Min Act: -0.1700
Data Index: 5349180 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.7880. Min Act: -0.1700
Data Index: 378460 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.7880. Min Act: -0.1700
Data Index: 634885 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.7880. Min Act: -0.1700
Data Index: 3702690 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19