Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.9200. Min Act: -0.1700
Data Index: 8222951 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.8575. Min Act: -0.1700
Data Index: 6439139 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.7325. Min Act: -0.1700
Data Index: 7893957 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.7012. Min Act: -0.1700
Data Index: 4569992 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.5762. Min Act: -0.1700
Data Index: 4266842 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.5450. Min Act: -0.1700
Data Index: 5297184 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.4825. Min Act: -0.1700
Data Index: 1178143 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.4512. Min Act: -0.1700
Data Index: 1682833 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.4200. Min Act: -0.1700
Data Index: 3649078 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.4200. Min Act: -0.1700
Data Index: 1046453 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.4200. Min Act: -0.1700
Data Index: 2157080 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.3887. Min Act: -0.1700
Data Index: 4006010 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.3887. Min Act: -0.1700
Data Index: 4215894 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.3575. Min Act: -0.1700
Data Index: 7419769 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.3262. Min Act: -0.1700
Data Index: 29253 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.3262. Min Act: -0.1700
Data Index: 2970848 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.3262. Min Act: -0.1700
Data Index: 8589306 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.3262. Min Act: -0.1700
Data Index: 7803942 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.3262. Min Act: -0.1700
Data Index: 2090573 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9200. Min Range: -7.9200
Max Act: 7.2950. Min Act: -0.1700
Data Index: 5343883 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19