Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2642 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1249. Min Range: -7.1249
Max Act: 7.1249. Min Act: -0.1700
Data Index: 2987488 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.9999. Min Act: -0.1700
Data Index: 4037761 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.9999. Min Act: -0.1700
Data Index: 6407929 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.9374. Min Act: -0.1700
Data Index: 4512261 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.9374. Min Act: -0.1700
Data Index: 4318769 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.8749. Min Act: -0.1700
Data Index: 420935 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.8437. Min Act: -0.1700
Data Index: 8539482 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.8124. Min Act: -0.1700
Data Index: 3316730 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.8124. Min Act: -0.1700
Data Index: 5428383 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.7812. Min Act: -0.1700
Data Index: 709687 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.7499. Min Act: -0.1700
Data Index: 3439782 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.7187. Min Act: -0.1700
Data Index: 4399489 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.6874. Min Act: -0.1700
Data Index: 75972 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.6874. Min Act: -0.1700
Data Index: 7950362 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.6874. Min Act: -0.1700
Data Index: 559852 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.6874. Min Act: -0.1700
Data Index: 682601 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.7187. Min Act: -0.1700
Data Index: 3600291 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.6562. Min Act: -0.1700
Data Index: 1569764 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.6562. Min Act: -0.1700
Data Index: 6218543 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1249. Min Range: -7.1249
Max Act: 6.6562. Min Act: -0.1700
Data Index: 3704227 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19