Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3683 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.8857. Min Act: -0.1700
Data Index: 7636559 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.7919. Min Act: -0.1700
Data Index: 3400989 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.7294. Min Act: -0.1700
Data Index: 950833 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.7294. Min Act: -0.1700
Data Index: 6784878 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.7294. Min Act: -0.1700
Data Index: 8802346 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.7294. Min Act: -0.1700
Data Index: 6810932 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.6669. Min Act: -0.1700
Data Index: 7281441 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.6357. Min Act: -0.1700
Data Index: 232568 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.6669. Min Act: -0.1700
Data Index: 3040415 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.6357. Min Act: -0.1700
Data Index: 3774110 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.6357. Min Act: -0.1700
Data Index: 4452634 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.6044. Min Act: -0.1700
Data Index: 2973785 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.6044. Min Act: -0.1700
Data Index: 4539850 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.5732. Min Act: -0.1700
Data Index: 8321952 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.5732. Min Act: -0.1700
Data Index: 8720735 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.5732. Min Act: -0.1700
Data Index: 5209152 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.5732. Min Act: -0.1700
Data Index: 1810476 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.5419. Min Act: -0.1700
Data Index: 2928187 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.5107. Min Act: -0.1700
Data Index: 5174837 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8857. Min Range: -5.8857
Max Act: 5.5419. Min Act: -0.1700
Data Index: 8558446 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19