Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3837 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1639. Min Range: -7.1639
Max Act: 7.1639. Min Act: -0.1700
Data Index: 7679665 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.9764. Min Act: -0.1700
Data Index: 8084571 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.9452. Min Act: -0.1700
Data Index: 3499806 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.9139. Min Act: -0.1700
Data Index: 4383523 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.8202. Min Act: -0.1700
Data Index: 5473786 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.7577. Min Act: -0.1700
Data Index: 7202149 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.7577. Min Act: -0.1700
Data Index: 6373435 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.6952. Min Act: -0.1700
Data Index: 7386661 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.6952. Min Act: -0.1700
Data Index: 6584620 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.6639. Min Act: -0.1700
Data Index: 2276926 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.6639. Min Act: -0.1700
Data Index: 694244 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.6327. Min Act: -0.1700
Data Index: 5670539 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.5702. Min Act: -0.1700
Data Index: 960014 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.5702. Min Act: -0.1700
Data Index: 6720122 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.5389. Min Act: -0.1700
Data Index: 5050435 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.5389. Min Act: -0.1700
Data Index: 5891176 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.5389. Min Act: -0.1700
Data Index: 2182838 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.5389. Min Act: -0.1700
Data Index: 1912564 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.5077. Min Act: -0.1700
Data Index: 1223007 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1639. Min Range: -7.1639
Max Act: 6.4764. Min Act: -0.1700
Data Index: 7826905 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19