Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4821. Min Range: -7.4821
Max Act: 7.4821. Min Act: -0.1700
Data Index: 7819585 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4821. Min Range: -7.4821
Max Act: 7.1383. Min Act: -0.1700
Data Index: 6866017 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4821. Min Range: -7.4821
Max Act: 7.1071. Min Act: -0.1700
Data Index: 825921 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.9821. Min Act: -0.1700
Data Index: 323908 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.9508. Min Act: -0.1700
Data Index: 162201 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.9196. Min Act: -0.1700
Data Index: 8625475 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.8883. Min Act: -0.1700
Data Index: 5296869 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.8883. Min Act: -0.1700
Data Index: 8723661 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.8258. Min Act: -0.1700
Data Index: 3882562 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.8258. Min Act: -0.1700
Data Index: 911425 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.7633. Min Act: -0.1700
Data Index: 1838763 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.7008. Min Act: -0.1700
Data Index: 2985323 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.7008. Min Act: -0.1700
Data Index: 8274441 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.6696. Min Act: -0.1700
Data Index: 2414035 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.6696. Min Act: -0.1700
Data Index: 3525692 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.6383. Min Act: -0.1700
Data Index: 1273350 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.6071. Min Act: -0.1700
Data Index: 7753958 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.6071. Min Act: -0.1700
Data Index: 5208414 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.6071. Min Act: -0.1700
Data Index: 3449712 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4821. Min Range: -7.4821
Max Act: 6.6071. Min Act: -0.1700
Data Index: 7910225 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19