Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.9973. Min Act: -0.1700
Data Index: 4496536 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.9973. Min Act: -0.1700
Data Index: 6528921 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.8723. Min Act: -0.1700
Data Index: 913949 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.7473. Min Act: -0.1700
Data Index: 3694622 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.6848. Min Act: -0.1700
Data Index: 425913 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.5598. Min Act: -0.1700
Data Index: 8239733 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.5598. Min Act: -0.1700
Data Index: 3437946 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.5598. Min Act: -0.1700
Data Index: 6505603 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.5598. Min Act: -0.1700
Data Index: 5108203 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.4973. Min Act: -0.1700
Data Index: 6621216 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.4973. Min Act: -0.1700
Data Index: 1180973 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.5598. Min Act: -0.1700
Data Index: 1231740 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.4973. Min Act: -0.1700
Data Index: 2631856 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.4348. Min Act: -0.1700
Data Index: 7270137 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.5598. Min Act: -0.1700
Data Index: 7179411 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.4348. Min Act: -0.1700
Data Index: 6074968 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.4348. Min Act: -0.1700
Data Index: 4916505 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.4348. Min Act: -0.1700
Data Index: 4728067 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.4348. Min Act: -0.1700
Data Index: 3065864 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9973. Min Range: -8.9973
Max Act: 8.4348. Min Act: -0.1700
Data Index: 7317916 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19