Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1691 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3383. Min Range: -9.3383
Max Act: 9.3383. Min Act: -0.1700
Data Index: 6560936 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3383. Min Range: -9.3383
Max Act: 9.2758. Min Act: -0.1700
Data Index: 2499062 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3383. Min Range: -9.3383
Max Act: 9.2758. Min Act: -0.1700
Data Index: 6314963 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3383. Min Range: -9.3383
Max Act: 9.2758. Min Act: -0.1700
Data Index: 3362962 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3383. Min Range: -9.3383
Max Act: 9.2133. Min Act: -0.1700
Data Index: 7338578 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3383. Min Range: -9.3383
Max Act: 9.2133. Min Act: -0.1700
Data Index: 2677051 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3383. Min Range: -9.3383
Max Act: 9.1508. Min Act: -0.1700
Data Index: 3309392 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3383. Min Range: -9.3383
Max Act: 9.0883. Min Act: -0.1700
Data Index: 6048585 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.9633. Min Act: -0.1700
Data Index: 775872 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.8383. Min Act: -0.1700
Data Index: 1726781 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.9633. Min Act: -0.1700
Data Index: 7294974 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.9633. Min Act: -0.1700
Data Index: 8396802 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.9008. Min Act: -0.1700
Data Index: 4967865 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.8383. Min Act: -0.1700
Data Index: 4540303 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.8383. Min Act: -0.1700
Data Index: 635903 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.8383. Min Act: -0.1700
Data Index: 775874 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.8383. Min Act: -0.1700
Data Index: 506016 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.8383. Min Act: -0.1700
Data Index: 3598155 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.7758. Min Act: -0.1700
Data Index: 775873 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3383. Min Range: -9.3383
Max Act: 8.7133. Min Act: -0.1700
Data Index: 3687051 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19