Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3235 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4435. Min Range: -7.4435
Max Act: 7.4435. Min Act: -0.1700
Data Index: 8185591 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.6622. Min Act: -0.1700
Data Index: 8378081 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.5997. Min Act: -0.1700
Data Index: 6481948 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.5372. Min Act: -0.1700
Data Index: 2781447 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.5060. Min Act: -0.1700
Data Index: 6280439 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.5372. Min Act: -0.1700
Data Index: 7097356 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.5372. Min Act: -0.1700
Data Index: 6799808 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.5060. Min Act: -0.1700
Data Index: 3515375 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.4747. Min Act: -0.1700
Data Index: 3203525 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.4435. Min Act: -0.1700
Data Index: 2590653 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.4435. Min Act: -0.1700
Data Index: 7097355 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.4435. Min Act: -0.1700
Data Index: 2781450 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.4435. Min Act: -0.1700
Data Index: 3420898 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.4435. Min Act: -0.1700
Data Index: 7097353 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.4122. Min Act: -0.1700
Data Index: 7360216 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.4435. Min Act: -0.1700
Data Index: 2199040 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.4435. Min Act: -0.1700
Data Index: 1013969 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.4122. Min Act: -0.1700
Data Index: 2087167 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.3810. Min Act: -0.1700
Data Index: 3597757 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4435. Min Range: -7.4435
Max Act: 6.3810. Min Act: -0.1700
Data Index: 3878484 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19