Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.4725. Min Act: -0.1700
Data Index: 7131856 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.3162. Min Act: -0.1700
Data Index: 7912160 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.2225. Min Act: -0.1700
Data Index: 8163421 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.2225. Min Act: -0.1700
Data Index: 7650098 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.1600. Min Act: -0.1700
Data Index: 7710302 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.0975. Min Act: -0.1700
Data Index: 7636362 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.0662. Min Act: -0.1700
Data Index: 4448286 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.0350. Min Act: -0.1700
Data Index: 7189377 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.0662. Min Act: -0.1700
Data Index: 6923056 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.0662. Min Act: -0.1700
Data Index: 7965622 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4725. Min Range: -8.4725
Max Act: 8.0037. Min Act: -0.1700
Data Index: 5802768 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4725. Min Range: -8.4725
Max Act: 7.9412. Min Act: -0.1700
Data Index: 5634477 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4725. Min Range: -8.4725
Max Act: 7.9412. Min Act: -0.1700
Data Index: 5945169 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4725. Min Range: -8.4725
Max Act: 7.8787. Min Act: -0.1700
Data Index: 2201300 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4725. Min Range: -8.4725
Max Act: 7.8787. Min Act: -0.1700
Data Index: 2902968 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4725. Min Range: -8.4725
Max Act: 7.8475. Min Act: -0.1700
Data Index: 3677084 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4725. Min Range: -8.4725
Max Act: 7.8162. Min Act: -0.1700
Data Index: 185055 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4725. Min Range: -8.4725
Max Act: 7.7850. Min Act: -0.1700
Data Index: 758455 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4725. Min Range: -8.4725
Max Act: 7.7537. Min Act: -0.1700
Data Index: 2556447 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4725. Min Range: -8.4725
Max Act: 7.7537. Min Act: -0.1700
Data Index: 445999 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19