Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3702 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.1166. Min Act: -0.1700
Data Index: 6119706 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0853. Min Act: -0.1700
Data Index: 5824732 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0853. Min Act: -0.1700
Data Index: 2927282 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0541. Min Act: -0.1700
Data Index: 6751301 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0541. Min Act: -0.1700
Data Index: 6318435 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0541. Min Act: -0.1700
Data Index: 603754 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0228. Min Act: -0.1700
Data Index: 893915 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0228. Min Act: -0.1700
Data Index: 2386830 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0228. Min Act: -0.1700
Data Index: 7073601 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0228. Min Act: -0.1700
Data Index: 3686552 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0228. Min Act: -0.1700
Data Index: 503746 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0228. Min Act: -0.1700
Data Index: 4006793 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1166. Min Range: -4.1166
Max Act: 4.0228. Min Act: -0.1700
Data Index: 1439541 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1166. Min Range: -4.1166
Max Act: 3.9916. Min Act: -0.1700
Data Index: 3567113 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1166. Min Range: -4.1166
Max Act: 3.9916. Min Act: -0.1700
Data Index: 3822662 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1166. Min Range: -4.1166
Max Act: 3.9916. Min Act: -0.1700
Data Index: 3976250 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1166. Min Range: -4.1166
Max Act: 3.9916. Min Act: -0.1700
Data Index: 5211951 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1166. Min Range: -4.1166
Max Act: 3.9916. Min Act: -0.1700
Data Index: 5268692 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1166. Min Range: -4.1166
Max Act: 3.9916. Min Act: -0.1700
Data Index: 5268693 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1166. Min Range: -4.1166
Max Act: 3.9916. Min Act: -0.1700
Data Index: 5356436 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19