Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4995 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1458. Min Range: -6.1458
Max Act: 6.0833. Min Act: -0.1700
Data Index: 6443927 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1458. Min Range: -6.1458
Max Act: 6.1146. Min Act: -0.1700
Data Index: 4867978 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1458. Min Range: -6.1458
Max Act: 6.1458. Min Act: -0.1700
Data Index: 1548932 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1458. Min Range: -6.1458
Max Act: 6.0833. Min Act: -0.1700
Data Index: 2707737 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1458. Min Range: -6.1458
Max Act: 6.0833. Min Act: -0.1700
Data Index: 580940 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.9583. Min Act: -0.1700
Data Index: 5774812 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.9583. Min Act: -0.1700
Data Index: 4789601 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.9583. Min Act: -0.1700
Data Index: 2281206 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.9583. Min Act: -0.1700
Data Index: 2087761 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.9583. Min Act: -0.1700
Data Index: 8308770 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.9896. Min Act: -0.1700
Data Index: 8160942 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.9583. Min Act: -0.1700
Data Index: 4958486 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.9271. Min Act: -0.1700
Data Index: 5195416 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.9271. Min Act: -0.1700
Data Index: 276931 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.8958. Min Act: -0.1700
Data Index: 7073248 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.8646. Min Act: -0.1700
Data Index: 2590930 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.8646. Min Act: -0.1700
Data Index: 4515581 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.8646. Min Act: -0.1698
Data Index: 3058632 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.8646. Min Act: -0.1700
Data Index: 2382934 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.8646. Min Act: -0.1700
Data Index: 5892492 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19