Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2851. Min Range: -6.2851
Max Act: 6.2851. Min Act: -0.1700
Data Index: 6493440 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2851. Min Range: -6.2851
Max Act: 6.2226. Min Act: -0.1700
Data Index: 82138 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.9726. Min Act: -0.1700
Data Index: 5942776 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.8788. Min Act: -0.1700
Data Index: 4502909 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.7538. Min Act: -0.1700
Data Index: 5991896 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.7226. Min Act: -0.1700
Data Index: 1133390 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.6913. Min Act: -0.1700
Data Index: 5527554 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.7226. Min Act: -0.1700
Data Index: 2121463 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.6601. Min Act: -0.1700
Data Index: 4127153 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.6601. Min Act: -0.1700
Data Index: 6462851 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.6288. Min Act: -0.1700
Data Index: 2572284 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.6288. Min Act: -0.1700
Data Index: 3511510 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.5976. Min Act: -0.1700
Data Index: 2272295 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.5976. Min Act: -0.1700
Data Index: 8224295 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.5976. Min Act: -0.1700
Data Index: 2588893 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.5976. Min Act: -0.1700
Data Index: 4228126 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.5976. Min Act: -0.1700
Data Index: 643166 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.5038. Min Act: -0.1700
Data Index: 681429 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.5038. Min Act: -0.1700
Data Index: 147045 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2851. Min Range: -6.2851
Max Act: 5.5038. Min Act: -0.1700
Data Index: 1943393 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19