Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.9739. Min Act: -0.1700
Data Index: 6661873 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.9113. Min Act: -0.1700
Data Index: 2488474 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8801. Min Act: -0.1700
Data Index: 2648560 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8488. Min Act: -0.1700
Data Index: 3385726 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8488. Min Act: -0.1700
Data Index: 1223488 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8488. Min Act: -0.1700
Data Index: 1449997 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8488. Min Act: -0.1700
Data Index: 1442199 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8488. Min Act: -0.1700
Data Index: 3986123 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8488. Min Act: -0.1700
Data Index: 5743694 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8488. Min Act: -0.1700
Data Index: 2805324 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8488. Min Act: -0.1700
Data Index: 1410121 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8488. Min Act: -0.1700
Data Index: 897048 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8175. Min Act: -0.1700
Data Index: 768481 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8175. Min Act: -0.1700
Data Index: 6531609 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8175. Min Act: -0.1700
Data Index: 346838 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8175. Min Act: -0.1700
Data Index: 1594841 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.8175. Min Act: -0.1700
Data Index: 2386833 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.7863. Min Act: -0.1700
Data Index: 2733817 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.7550. Min Act: -0.1700
Data Index: 258756 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9739. Min Range: -3.9739
Max Act: 3.7863. Min Act: -0.1700
Data Index: 2331851 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19