Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1965. Min Range: -7.1965
Max Act: 7.1965. Min Act: -0.1700
Data Index: 508898 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1965. Min Range: -7.1965
Max Act: 7.0715. Min Act: -0.1700
Data Index: 1489750 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1965. Min Range: -7.1965
Max Act: 7.0403. Min Act: -0.1700
Data Index: 1848828 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1965. Min Range: -7.1965
Max Act: 7.0090. Min Act: -0.1700
Data Index: 1856388 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.7903. Min Act: -0.1700
Data Index: 7176910 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.7903. Min Act: -0.1700
Data Index: 4021184 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.7903. Min Act: -0.1700
Data Index: 2271645 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.7903. Min Act: -0.1700
Data Index: 6423021 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.7278. Min Act: -0.1700
Data Index: 6379660 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.7278. Min Act: -0.1700
Data Index: 466767 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.7278. Min Act: -0.1700
Data Index: 8715732 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.6340. Min Act: -0.1700
Data Index: 4729445 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.6340. Min Act: -0.1700
Data Index: 3744666 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.6028. Min Act: -0.1700
Data Index: 3958561 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.6028. Min Act: -0.1700
Data Index: 1562420 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.5403. Min Act: -0.1700
Data Index: 5042716 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.5403. Min Act: -0.1700
Data Index: 2464633 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.5090. Min Act: -0.1700
Data Index: 437060 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.5715. Min Act: -0.1700
Data Index: 481319 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1965. Min Range: -7.1965
Max Act: 6.4778. Min Act: -0.1700
Data Index: 5334288 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19