Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.6968. Min Act: -0.1700
Data Index: 754261 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.2905. Min Act: -0.1700
Data Index: 8116391 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1968. Min Act: -0.1700
Data Index: 6412439 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1343. Min Act: -0.1700
Data Index: 4528096 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1343. Min Act: -0.1700
Data Index: 7308016 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1655. Min Act: -0.1700
Data Index: 8254388 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.0405. Min Act: -0.1700
Data Index: 17817 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.0093. Min Act: -0.1700
Data Index: 1758730 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.9780. Min Act: -0.1700
Data Index: 7142930 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.9468. Min Act: -0.1700
Data Index: 1496220 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.9155. Min Act: -0.1700
Data Index: 5539695 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.9155. Min Act: -0.1700
Data Index: 1229595 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.8530. Min Act: -0.1700
Data Index: 7016152 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.8843. Min Act: -0.1700
Data Index: 5067504 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.8530. Min Act: -0.1700
Data Index: 8000995 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.8218. Min Act: -0.1700
Data Index: 2576379 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.7905. Min Act: -0.1700
Data Index: 8416812 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.7905. Min Act: -0.1700
Data Index: 7065660 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.8218. Min Act: -0.1700
Data Index: 2198112 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6968. Min Range: -6.6968
Max Act: 5.7905. Min Act: -0.1700
Data Index: 1588670 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19