Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 676 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7793. Min Range: -9.7793
Max Act: 9.7793. Min Act: -0.1700
Data Index: 8660298 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7793. Min Range: -9.7793
Max Act: 9.5293. Min Act: -0.1700
Data Index: 7028741 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7793. Min Range: -9.7793
Max Act: 9.4668. Min Act: -0.1700
Data Index: 3221937 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7793. Min Range: -9.7793
Max Act: 9.3418. Min Act: -0.1700
Data Index: 1543897 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7793. Min Range: -9.7793
Max Act: 9.3418. Min Act: -0.1700
Data Index: 8322961 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7793. Min Range: -9.7793
Max Act: 9.2168. Min Act: -0.1700
Data Index: 4488412 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.8418. Min Act: -0.1700
Data Index: 94942 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.8418. Min Act: -0.1700
Data Index: 8346779 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7793. Min Act: -0.1700
Data Index: 677929 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7793. Min Act: -0.1700
Data Index: 5795144 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7793. Min Act: -0.1700
Data Index: 6836013 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7793. Min Act: -0.1700
Data Index: 4422508 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7793. Min Act: -0.1700
Data Index: 8827392 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7793. Min Act: -0.1700
Data Index: 178896 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7168. Min Act: -0.1700
Data Index: 8426139 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7168. Min Act: -0.1700
Data Index: 3529513 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7168. Min Act: -0.1700
Data Index: 8202081 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7168. Min Act: -0.1700
Data Index: 2331439 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7168. Min Act: -0.1700
Data Index: 6331836 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7793. Min Range: -9.7793
Max Act: 8.7168. Min Act: -0.1700
Data Index: 4786462 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19