Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2937 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1918. Min Range: -6.1918
Max Act: 6.1918. Min Act: -0.1700
Data Index: 3618178 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1918. Min Range: -6.1918
Max Act: 6.0355. Min Act: -0.1700
Data Index: 459228 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.8793. Min Act: -0.1700
Data Index: 956927 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.8793. Min Act: -0.1700
Data Index: 829596 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.8168. Min Act: -0.1700
Data Index: 6178213 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.7855. Min Act: -0.1700
Data Index: 6203246 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.7855. Min Act: -0.1700
Data Index: 1937572 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.7543. Min Act: -0.1700
Data Index: 494281 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.7230. Min Act: -0.1700
Data Index: 3093718 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6918. Min Act: -0.1700
Data Index: 709423 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6918. Min Act: -0.1700
Data Index: 7995647 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6918. Min Act: -0.1700
Data Index: 6458350 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6605. Min Act: -0.1700
Data Index: 1741065 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6293. Min Act: -0.1700
Data Index: 5006276 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6293. Min Act: -0.1700
Data Index: 574596 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6293. Min Act: -0.1700
Data Index: 5255824 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6293. Min Act: -0.1700
Data Index: 7859658 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6293. Min Act: -0.1700
Data Index: 5206557 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6293. Min Act: -0.1700
Data Index: 6665704 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1918. Min Range: -6.1918
Max Act: 5.6293. Min Act: -0.1700
Data Index: 3989893 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19