Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4419 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.7665. Min Act: -0.1700
Data Index: 8513661 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.7499. Min Act: -0.1700
Data Index: 1023102 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.7416. Min Act: -0.1700
Data Index: 2606396 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.7334. Min Act: -0.1700
Data Index: 1172315 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.7251. Min Act: -0.1700
Data Index: 398972 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.7169. Min Act: -0.1700
Data Index: 280560 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.7006. Min Act: -0.1700
Data Index: 744861 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.7006. Min Act: -0.1700
Data Index: 725072 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.7006. Min Act: -0.1700
Data Index: 8048044 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6924. Min Act: -0.1700
Data Index: 552038 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6924. Min Act: -0.1699
Data Index: 5407760 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6843. Min Act: -0.1700
Data Index: 5906848 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6843. Min Act: -0.1700
Data Index: 7035225 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6843. Min Act: -0.1699
Data Index: 7375625 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6843. Min Act: -0.1700
Data Index: 6842033 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6843. Min Act: -0.1699
Data Index: 5540799 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6762. Min Act: -0.1700
Data Index: 2684576 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6762. Min Act: -0.1700
Data Index: 6130439 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6762. Min Act: -0.1700
Data Index: 6809972 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7665. Min Range: -0.7665
Max Act: 0.6762. Min Act: -0.1700
Data Index: 2006252 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19