Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 782 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3500. Min Range: -5.3500
Max Act: 5.3500. Min Act: -0.1700
Data Index: 4461547 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3500. Min Range: -5.3500
Max Act: 5.1625. Min Act: -0.1700
Data Index: 8385801 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3500. Min Range: -5.3500
Max Act: 5.1313. Min Act: -0.1700
Data Index: 7085755 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3500. Min Range: -5.3500
Max Act: 5.0688. Min Act: -0.1700
Data Index: 7433645 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3500. Min Range: -5.3500
Max Act: 5.0375. Min Act: -0.1700
Data Index: 4686425 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3500. Min Range: -5.3500
Max Act: 5.0375. Min Act: -0.1700
Data Index: 8664451 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.9750. Min Act: -0.1700
Data Index: 1955157 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.9750. Min Act: -0.1700
Data Index: 3068934 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.9125. Min Act: -0.1700
Data Index: 6800228 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.9125. Min Act: -0.1700
Data Index: 1647172 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.9125. Min Act: -0.1700
Data Index: 3295962 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.9125. Min Act: -0.1700
Data Index: 2064027 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.8813. Min Act: -0.1700
Data Index: 1172546 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.8813. Min Act: -0.1700
Data Index: 8188647 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.8813. Min Act: -0.1700
Data Index: 7096902 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.8500. Min Act: -0.1700
Data Index: 2246874 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.7563. Min Act: -0.1700
Data Index: 114191 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.7875. Min Act: -0.1700
Data Index: 8739345 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.7875. Min Act: -0.1700
Data Index: 8019696 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3500. Min Range: -5.3500
Max Act: 4.7563. Min Act: -0.1700
Data Index: 7839634 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19