Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1053. Min Range: -5.1053
Max Act: 5.1053. Min Act: -0.1700
Data Index: 8599410 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1053. Min Range: -5.1053
Max Act: 5.0740. Min Act: -0.1700
Data Index: 5248857 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1053. Min Range: -5.1053
Max Act: 5.0740. Min Act: -0.1700
Data Index: 4270271 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1053. Min Range: -5.1053
Max Act: 5.0740. Min Act: -0.1700
Data Index: 1365723 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1053. Min Range: -5.1053
Max Act: 5.0428. Min Act: -0.1700
Data Index: 3392033 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1053. Min Range: -5.1053
Max Act: 5.0740. Min Act: -0.1700
Data Index: 1640043 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1053. Min Range: -5.1053
Max Act: 5.0115. Min Act: -0.1700
Data Index: 1909987 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1053. Min Range: -5.1053
Max Act: 5.0115. Min Act: -0.1700
Data Index: 5331080 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1053. Min Range: -5.1053
Max Act: 5.0115. Min Act: -0.1700
Data Index: 8170901 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1053. Min Range: -5.1053
Max Act: 5.0115. Min Act: -0.1700
Data Index: 2079867 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1053. Min Range: -5.1053
Max Act: 4.9803. Min Act: -0.1700
Data Index: 3293757 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1053. Min Range: -5.1053
Max Act: 4.9803. Min Act: -0.1700
Data Index: 1408772 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1053. Min Range: -5.1053
Max Act: 4.9490. Min Act: -0.1700
Data Index: 373267 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1053. Min Range: -5.1053
Max Act: 4.9490. Min Act: -0.1700
Data Index: 1783568 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1053. Min Range: -5.1053
Max Act: 4.9490. Min Act: -0.1700
Data Index: 8426188 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1053. Min Range: -5.1053
Max Act: 4.9490. Min Act: -0.1700
Data Index: 4823930 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1053. Min Range: -5.1053
Max Act: 4.9490. Min Act: -0.1700
Data Index: 168404 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1053. Min Range: -5.1053
Max Act: 4.9490. Min Act: -0.1700
Data Index: 6473219 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1053. Min Range: -5.1053
Max Act: 4.9490. Min Act: -0.1700
Data Index: 5268051 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1053. Min Range: -5.1053
Max Act: 4.9803. Min Act: -0.1700
Data Index: 4961846 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19