Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3115. Min Range: -6.3115
Max Act: 6.3115. Min Act: -0.1700
Data Index: 7083600 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3115. Min Range: -6.3115
Max Act: 6.1865. Min Act: -0.1700
Data Index: 131709 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3115. Min Range: -6.3115
Max Act: 6.1553. Min Act: -0.1700
Data Index: 3185109 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3115. Min Range: -6.3115
Max Act: 6.1865. Min Act: -0.1700
Data Index: 5799883 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3115. Min Range: -6.3115
Max Act: 6.0928. Min Act: -0.1700
Data Index: 5079850 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3115. Min Range: -6.3115
Max Act: 6.0303. Min Act: -0.1700
Data Index: 2672918 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.9678. Min Act: -0.1700
Data Index: 1901221 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.9053. Min Act: -0.1700
Data Index: 7198934 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.9053. Min Act: -0.1700
Data Index: 7564315 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.9053. Min Act: -0.1700
Data Index: 7032766 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.8740. Min Act: -0.1700
Data Index: 996963 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.8740. Min Act: -0.1700
Data Index: 5525855 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.8740. Min Act: -0.1700
Data Index: 3844640 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.8428. Min Act: -0.1700
Data Index: 1044682 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.8115. Min Act: -0.1700
Data Index: 5530821 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.7490. Min Act: -0.1700
Data Index: 7200259 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.7490. Min Act: -0.1700
Data Index: 71016 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.7803. Min Act: -0.1700
Data Index: 8228944 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.7490. Min Act: -0.1700
Data Index: 8201847 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3115. Min Range: -6.3115
Max Act: 5.7490. Min Act: -0.1700
Data Index: 2933448 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19