Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1780 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1885. Min Range: -8.1885
Max Act: 8.1885. Min Act: -0.1700
Data Index: 6645072 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.8760. Min Act: -0.1700
Data Index: 4057085 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.8760. Min Act: -0.1700
Data Index: 3557274 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.7510. Min Act: -0.1700
Data Index: 4107315 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.6885. Min Act: -0.1700
Data Index: 6489331 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.6260. Min Act: -0.1700
Data Index: 4386550 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.5947. Min Act: -0.1700
Data Index: 6043888 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.5635. Min Act: -0.1700
Data Index: 3854130 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.4697. Min Act: -0.1700
Data Index: 1955030 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.4385. Min Act: -0.1700
Data Index: 8628574 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.4385. Min Act: -0.1700
Data Index: 3835261 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.4385. Min Act: -0.1700
Data Index: 7851327 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.4385. Min Act: -0.1700
Data Index: 5548327 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.4385. Min Act: -0.1700
Data Index: 3707800 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.4385. Min Act: -0.1700
Data Index: 5548326 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.4072. Min Act: -0.1700
Data Index: 192400 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.4072. Min Act: -0.1700
Data Index: 7621987 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.4072. Min Act: -0.1700
Data Index: 5927036 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.3760. Min Act: -0.1700
Data Index: 1036583 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1885. Min Range: -8.1885
Max Act: 7.3447. Min Act: -0.1700
Data Index: 2810645 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19