Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.9807. Min Act: -0.1700
Data Index: 5344245 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.4807. Min Act: -0.1700
Data Index: 57007 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.5120. Min Act: -0.1700
Data Index: 5353152 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.4182. Min Act: -0.1700
Data Index: 8710219 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.3870. Min Act: -0.1700
Data Index: 7741469 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.3557. Min Act: -0.1700
Data Index: 7074176 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.3557. Min Act: -0.1700
Data Index: 2440383 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.2932. Min Act: -0.1700
Data Index: 6807497 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.2620. Min Act: -0.1700
Data Index: 1161799 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.2620. Min Act: -0.1700
Data Index: 3164752 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.2620. Min Act: -0.1700
Data Index: 5241764 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.1682. Min Act: -0.1700
Data Index: 968423 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.1682. Min Act: -0.1700
Data Index: 211210 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.1682. Min Act: -0.1700
Data Index: 6905558 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.1682. Min Act: -0.1700
Data Index: 8515735 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.1370. Min Act: -0.1700
Data Index: 3573182 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.1370. Min Act: -0.1700
Data Index: 1941367 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.1370. Min Act: -0.1700
Data Index: 1587353 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.1057. Min Act: -0.1700
Data Index: 2650140 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9807. Min Range: -5.9807
Max Act: 5.1057. Min Act: -0.1700
Data Index: 2387804 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19