Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4137 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0807. Min Range: -5.0807
Max Act: 5.0807. Min Act: -0.1700
Data Index: 3907456 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0807. Min Range: -5.0807
Max Act: 5.0807. Min Act: -0.1700
Data Index: 6538801 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0807. Min Range: -5.0807
Max Act: 5.0494. Min Act: -0.1700
Data Index: 4789911 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.8932. Min Act: -0.1700
Data Index: 7539073 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.8619. Min Act: -0.1700
Data Index: 3978403 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.8619. Min Act: -0.1700
Data Index: 6498348 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.7994. Min Act: -0.1700
Data Index: 2605519 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.7682. Min Act: -0.1700
Data Index: 4352281 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.7682. Min Act: -0.1700
Data Index: 6210672 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.7682. Min Act: -0.1700
Data Index: 4788409 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.7994. Min Act: -0.1700
Data Index: 1867518 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.7682. Min Act: -0.1700
Data Index: 1408664 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.7682. Min Act: -0.1700
Data Index: 2689939 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.7057. Min Act: -0.1700
Data Index: 53587 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.7057. Min Act: -0.1700
Data Index: 4275164 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.6744. Min Act: -0.1700
Data Index: 3472977 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.7057. Min Act: -0.1700
Data Index: 398350 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.6744. Min Act: -0.1700
Data Index: 1000110 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.6744. Min Act: -0.1700
Data Index: 4870086 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0807. Min Range: -5.0807
Max Act: 4.6744. Min Act: -0.1700
Data Index: 822876 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19