Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.6501. Min Act: -0.1700
Data Index: 1075718 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.6501. Min Act: -0.1700
Data Index: 4179946 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.5251. Min Act: -0.1700
Data Index: 1241055 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.4626. Min Act: -0.1700
Data Index: 4242230 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.4001. Min Act: -0.1700
Data Index: 2878897 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.2751. Min Act: -0.1700
Data Index: 1147242 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.3376. Min Act: -0.1700
Data Index: 6390110 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.2751. Min Act: -0.1700
Data Index: 4223871 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.2751. Min Act: -0.1700
Data Index: 6583362 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.2439. Min Act: -0.1700
Data Index: 3892187 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.2126. Min Act: -0.1700
Data Index: 1142943 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.2126. Min Act: -0.1700
Data Index: 7396486 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.1814. Min Act: -0.1700
Data Index: 5525751 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.1814. Min Act: -0.1700
Data Index: 5968260 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.1814. Min Act: -0.1700
Data Index: 2411031 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.1814. Min Act: -0.1700
Data Index: 4385443 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.1501. Min Act: -0.1700
Data Index: 2914216 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.1189. Min Act: -0.1700
Data Index: 1380112 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.1501. Min Act: -0.1700
Data Index: 166744 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6501. Min Range: -7.6501
Max Act: 7.0876. Min Act: -0.1700
Data Index: 812215 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19