Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4850 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3936. Min Range: -6.3936
Max Act: 6.3936. Min Act: -0.1700
Data Index: 6016599 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3936. Min Range: -6.3936
Max Act: 6.0499. Min Act: -0.1700
Data Index: 8757142 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.9874. Min Act: -0.1700
Data Index: 589118 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.8624. Min Act: -0.1700
Data Index: 478974 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.7374. Min Act: -0.1700
Data Index: 3479504 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.7686. Min Act: -0.1700
Data Index: 1433586 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.7374. Min Act: -0.1700
Data Index: 7132345 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.7061. Min Act: -0.1700
Data Index: 1667577 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.6436. Min Act: -0.1700
Data Index: 818369 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.6436. Min Act: -0.1700
Data Index: 3302814 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.6124. Min Act: -0.1700
Data Index: 8631942 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.5811. Min Act: -0.1700
Data Index: 5357221 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.5811. Min Act: -0.1700
Data Index: 5756645 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.5811. Min Act: -0.1700
Data Index: 8386796 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.5499. Min Act: -0.1700
Data Index: 3425386 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.5499. Min Act: -0.1700
Data Index: 2842886 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.5499. Min Act: -0.1700
Data Index: 4719776 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.5186. Min Act: -0.1700
Data Index: 211346 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.5186. Min Act: -0.1700
Data Index: 6273362 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3936. Min Range: -6.3936
Max Act: 5.5186. Min Act: -0.1700
Data Index: 3663379 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19