Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.1846. Min Act: -0.1700
Data Index: 617603 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.1221. Min Act: -0.1700
Data Index: 2416171 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0909. Min Act: -0.1700
Data Index: 4615680 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0909. Min Act: -0.1700
Data Index: 1252148 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0909. Min Act: -0.1700
Data Index: 4723961 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0909. Min Act: -0.1700
Data Index: 8436432 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0909. Min Act: -0.1700
Data Index: 4135502 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0596. Min Act: -0.1700
Data Index: 3638600 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0596. Min Act: -0.1700
Data Index: 6280801 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0284. Min Act: -0.1700
Data Index: 4344644 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0596. Min Act: -0.1700
Data Index: 798869 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0596. Min Act: -0.1700
Data Index: 5961907 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0596. Min Act: -0.1700
Data Index: 2235669 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0596. Min Act: -0.1700
Data Index: 6535962 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0596. Min Act: -0.1700
Data Index: 1318556 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1846. Min Range: -6.1846
Max Act: 6.0284. Min Act: -0.1700
Data Index: 1596973 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1846. Min Range: -6.1846
Max Act: 5.9971. Min Act: -0.1700
Data Index: 4135491 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1846. Min Range: -6.1846
Max Act: 5.9971. Min Act: -0.1700
Data Index: 6236750 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1846. Min Range: -6.1846
Max Act: 5.9971. Min Act: -0.1700
Data Index: 4525396 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1846. Min Range: -6.1846
Max Act: 5.9971. Min Act: -0.1700
Data Index: 4604010 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19