Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6918. Min Range: -8.6918
Max Act: 8.6918. Min Act: -0.1700
Data Index: 3199333 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6918. Min Range: -8.6918
Max Act: 8.5668. Min Act: -0.1700
Data Index: 3900036 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6918. Min Range: -8.6918
Max Act: 8.0668. Min Act: -0.1700
Data Index: 1530567 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6918. Min Range: -8.6918
Max Act: 8.0668. Min Act: -0.1700
Data Index: 4436663 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6918. Min Range: -8.6918
Max Act: 8.0043. Min Act: -0.1700
Data Index: 7881662 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.9418. Min Act: -0.1700
Data Index: 8024246 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.9418. Min Act: -0.1700
Data Index: 7776898 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.8793. Min Act: -0.1700
Data Index: 3830145 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.8793. Min Act: -0.1700
Data Index: 8813043 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.8168. Min Act: -0.1700
Data Index: 4686865 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.7543. Min Act: -0.1700
Data Index: 1440053 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.8168. Min Act: -0.1700
Data Index: 2649445 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.7543. Min Act: -0.1700
Data Index: 1075928 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.7543. Min Act: -0.1700
Data Index: 6452473 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.7543. Min Act: -0.1700
Data Index: 5758177 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.7543. Min Act: -0.1700
Data Index: 5396680 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.6918. Min Act: -0.1700
Data Index: 18836 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.7543. Min Act: -0.1700
Data Index: 2606546 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.8168. Min Act: -0.1700
Data Index: 5498282 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6918. Min Range: -8.6918
Max Act: 7.6918. Min Act: -0.1700
Data Index: 2497253 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19