Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3370 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2918. Min Range: -7.2918
Max Act: 7.2918. Min Act: -0.1700
Data Index: 1643484 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2918. Min Range: -7.2918
Max Act: 7.2293. Min Act: -0.1700
Data Index: 4775952 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2918. Min Range: -7.2918
Max Act: 7.1043. Min Act: -0.1700
Data Index: 5706852 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.9793. Min Act: -0.1700
Data Index: 5227737 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.9168. Min Act: -0.1700
Data Index: 3010732 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.9168. Min Act: -0.1700
Data Index: 3318001 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.8543. Min Act: -0.1700
Data Index: 5312500 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.8543. Min Act: -0.1700
Data Index: 8253537 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.8231. Min Act: -0.1700
Data Index: 6566799 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.7918. Min Act: -0.1700
Data Index: 7313458 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.7293. Min Act: -0.1700
Data Index: 7096681 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.6981. Min Act: -0.1700
Data Index: 2981214 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.6981. Min Act: -0.1700
Data Index: 4502872 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.6981. Min Act: -0.1700
Data Index: 3001436 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.6668. Min Act: -0.1700
Data Index: 7154381 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.6356. Min Act: -0.1700
Data Index: 869204 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.6356. Min Act: -0.1700
Data Index: 6151391 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.6356. Min Act: -0.1700
Data Index: 4317651 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.6356. Min Act: -0.1700
Data Index: 3337080 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2918. Min Range: -7.2918
Max Act: 6.6356. Min Act: -0.1700
Data Index: 3045660 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19