Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2780 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1614. Min Range: -6.1614
Max Act: 6.1614. Min Act: -0.1700
Data Index: 6815131 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1614. Min Range: -6.1614
Max Act: 6.0676. Min Act: -0.1700
Data Index: 6488649 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1614. Min Range: -6.1614
Max Act: 6.0051. Min Act: -0.1700
Data Index: 5071705 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.9114. Min Act: -0.1700
Data Index: 6663999 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.9114. Min Act: -0.1700
Data Index: 2094689 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.8801. Min Act: -0.1700
Data Index: 972799 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.8489. Min Act: -0.1700
Data Index: 6235647 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.8489. Min Act: -0.1700
Data Index: 1415058 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.8489. Min Act: -0.1700
Data Index: 6966662 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.8176. Min Act: -0.1700
Data Index: 4376858 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.8176. Min Act: -0.1700
Data Index: 3952706 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.7864. Min Act: -0.1700
Data Index: 3595652 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.7551. Min Act: -0.1700
Data Index: 3012800 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.7239. Min Act: -0.1700
Data Index: 257889 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.7239. Min Act: -0.1700
Data Index: 6684758 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.7239. Min Act: -0.1700
Data Index: 3781634 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.7239. Min Act: -0.1700
Data Index: 1828901 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.6926. Min Act: -0.1700
Data Index: 912648 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.6614. Min Act: -0.1700
Data Index: 2213131 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1614. Min Range: -6.1614
Max Act: 5.6614. Min Act: -0.1700
Data Index: 1481099 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19