Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2297 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.9814. Min Act: -0.1700
Data Index: 64854 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.9189. Min Act: -0.1700
Data Index: 6805476 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.8252. Min Act: -0.1700
Data Index: 4830982 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.7939. Min Act: -0.1700
Data Index: 8764977 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.7939. Min Act: -0.1700
Data Index: 7650288 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.7939. Min Act: -0.1700
Data Index: 3161569 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.7627. Min Act: -0.1700
Data Index: 2729019 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.7002. Min Act: -0.1700
Data Index: 7171721 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.7314. Min Act: -0.1700
Data Index: 6783804 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.7314. Min Act: -0.1700
Data Index: 7735891 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.7002. Min Act: -0.1700
Data Index: 5330349 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.7002. Min Act: -0.1700
Data Index: 1977016 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.6689. Min Act: -0.1700
Data Index: 7546747 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.6689. Min Act: -0.1700
Data Index: 1471153 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.6689. Min Act: -0.1700
Data Index: 2590747 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.6689. Min Act: -0.1700
Data Index: 5756624 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.6689. Min Act: -0.1700
Data Index: 5837127 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.6377. Min Act: -0.1700
Data Index: 4718986 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.6689. Min Act: -0.1700
Data Index: 314231 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9814. Min Range: -5.9814
Max Act: 5.6377. Min Act: -0.1700
Data Index: 6100178 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19