Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2773 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2009. Min Range: -6.2009
Max Act: 6.2009. Min Act: -0.1700
Data Index: 86276 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2009. Min Range: -6.2009
Max Act: 6.1071. Min Act: -0.1700
Data Index: 2448484 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.9196. Min Act: -0.1700
Data Index: 4353639 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.9196. Min Act: -0.1700
Data Index: 3835089 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.8884. Min Act: -0.1700
Data Index: 5534043 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.8571. Min Act: -0.1700
Data Index: 4953297 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.8571. Min Act: -0.1700
Data Index: 305480 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.8884. Min Act: -0.1700
Data Index: 6183159 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.8259. Min Act: -0.1700
Data Index: 6120931 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.7946. Min Act: -0.1700
Data Index: 2944490 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.7946. Min Act: -0.1700
Data Index: 3602296 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.7634. Min Act: -0.1700
Data Index: 296855 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.7321. Min Act: -0.1700
Data Index: 315583 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.6696. Min Act: -0.1700
Data Index: 5577757 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.7009. Min Act: -0.1700
Data Index: 905367 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.7009. Min Act: -0.1700
Data Index: 3562228 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.7009. Min Act: -0.1700
Data Index: 1882213 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.6696. Min Act: -0.1700
Data Index: 81098 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.6696. Min Act: -0.1700
Data Index: 5164813 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2009. Min Range: -6.2009
Max Act: 5.6696. Min Act: -0.1700
Data Index: 5899724 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19