Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.9983. Min Act: -0.1700
Data Index: 1053791 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.7171. Min Act: -0.1700
Data Index: 6493014 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.6233. Min Act: -0.1700
Data Index: 5163315 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.5921. Min Act: -0.1700
Data Index: 2888028 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.5608. Min Act: -0.1700
Data Index: 1086718 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.5608. Min Act: -0.1700
Data Index: 7400496 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.5608. Min Act: -0.1700
Data Index: 4524403 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.5608. Min Act: -0.1700
Data Index: 7999786 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4670. Min Act: -0.1700
Data Index: 5576850 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4670. Min Act: -0.1700
Data Index: 3811466 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4670. Min Act: -0.1700
Data Index: 7360001 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4670. Min Act: -0.1700
Data Index: 4891977 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4670. Min Act: -0.1700
Data Index: 7848554 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4983. Min Act: -0.1700
Data Index: 6376209 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4358. Min Act: -0.1700
Data Index: 8831539 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4358. Min Act: -0.1700
Data Index: 7400495 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4358. Min Act: -0.1700
Data Index: 762653 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4358. Min Act: -0.1700
Data Index: 7400511 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4358. Min Act: -0.1700
Data Index: 3002781 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9983. Min Range: -4.9983
Max Act: 4.4358. Min Act: -0.1700
Data Index: 6868 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19