Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2668 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5881. Min Range: -7.5881
Max Act: 7.5881. Min Act: -0.1700
Data Index: 1166046 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5881. Min Range: -7.5881
Max Act: 7.5881. Min Act: -0.1700
Data Index: 2311388 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5881. Min Range: -7.5881
Max Act: 7.5256. Min Act: -0.1700
Data Index: 3943637 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5881. Min Range: -7.5881
Max Act: 7.4318. Min Act: -0.1700
Data Index: 4365746 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5881. Min Range: -7.5881
Max Act: 7.3693. Min Act: -0.1700
Data Index: 3678264 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5881. Min Range: -7.5881
Max Act: 7.2756. Min Act: -0.1700
Data Index: 1916286 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5881. Min Range: -7.5881
Max Act: 7.1193. Min Act: -0.1700
Data Index: 3697623 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5881. Min Range: -7.5881
Max Act: 7.0256. Min Act: -0.1700
Data Index: 789012 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5881. Min Range: -7.5881
Max Act: 7.0568. Min Act: -0.1700
Data Index: 1424473 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.9943. Min Act: -0.1700
Data Index: 6181832 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.9943. Min Act: -0.1700
Data Index: 167963 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.9318. Min Act: -0.1700
Data Index: 2481252 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.9318. Min Act: -0.1700
Data Index: 8696798 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.9006. Min Act: -0.1700
Data Index: 6426964 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.8693. Min Act: -0.1700
Data Index: 5179770 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.8068. Min Act: -0.1700
Data Index: 986043 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.8381. Min Act: -0.1700
Data Index: 4364794 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.7756. Min Act: -0.1700
Data Index: 5620550 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.8068. Min Act: -0.1700
Data Index: 1736558 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5881. Min Range: -7.5881
Max Act: 6.8068. Min Act: -0.1700
Data Index: 5196627 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19