Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 312 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9923. Min Act: -0.1700
Data Index: 8350851 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 6775499 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 6737745 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 4830466 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 3123728 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 5334092 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 6833368 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 5324405 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8048. Min Act: -0.1700
Data Index: 2621885 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 7698115 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8048. Min Act: -0.1700
Data Index: 7527036 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7736. Min Act: -0.1700
Data Index: 5979185 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7736. Min Act: -0.1700
Data Index: 7948505 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7736. Min Act: -0.1700
Data Index: 2532276 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7736. Min Act: -0.1700
Data Index: 4190078 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 2754194 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 1864425 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 1206096 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7111. Min Act: -0.1700
Data Index: 2154437 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 7607506 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19