Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2529 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0752. Min Range: -7.0752
Max Act: 7.0752. Min Act: -0.1700
Data Index: 8798738 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0752. Min Range: -7.0752
Max Act: 7.0752. Min Act: -0.1700
Data Index: 6324459 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0752. Min Range: -7.0752
Max Act: 7.0752. Min Act: -0.1700
Data Index: 4480941 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0752. Min Range: -7.0752
Max Act: 7.0127. Min Act: -0.1700
Data Index: 8136775 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.9815. Min Act: -0.1700
Data Index: 2605637 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.9502. Min Act: -0.1700
Data Index: 8736940 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.9815. Min Act: -0.1700
Data Index: 3156201 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.9502. Min Act: -0.1700
Data Index: 674639 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.8877. Min Act: -0.1700
Data Index: 5483142 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.8565. Min Act: -0.1700
Data Index: 5201764 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.8252. Min Act: -0.1700
Data Index: 2331229 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.8565. Min Act: -0.1700
Data Index: 3857475 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.8565. Min Act: -0.1700
Data Index: 2246154 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.8565. Min Act: -0.1700
Data Index: 2573541 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.8252. Min Act: -0.1700
Data Index: 7322254 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.7940. Min Act: -0.1700
Data Index: 5131720 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.7940. Min Act: -0.1700
Data Index: 5259283 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.8252. Min Act: -0.1700
Data Index: 3807534 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.8252. Min Act: -0.1700
Data Index: 6140311 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0752. Min Range: -7.0752
Max Act: 6.7940. Min Act: -0.1700
Data Index: 1328070 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19