Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 866 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.8791. Min Act: -0.1700
Data Index: 7601854 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.6916. Min Act: -0.1700
Data Index: 2460484 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.6291. Min Act: -0.1700
Data Index: 1483470 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.4416. Min Act: -0.1700
Data Index: 6626135 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.3791. Min Act: -0.1700
Data Index: 1275923 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.3166. Min Act: -0.1700
Data Index: 5898876 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.3166. Min Act: -0.1700
Data Index: 7254725 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.2541. Min Act: -0.1700
Data Index: 5281272 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.2541. Min Act: -0.1700
Data Index: 2704376 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 1968843 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 382661 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 26099 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 8424780 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 1646775 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.0666. Min Act: -0.1700
Data Index: 8252712 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1291. Min Act: -0.1700
Data Index: 1986964 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 8747020 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1291. Min Act: -0.1700
Data Index: 4473483 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1291. Min Act: -0.1700
Data Index: 3374545 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.0666. Min Act: -0.1700
Data Index: 2173618 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19