Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2507 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0262. Min Range: -8.0262
Max Act: 8.0262. Min Act: -0.1700
Data Index: 2288147 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.9637. Min Act: -0.1700
Data Index: 770178 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.9012. Min Act: -0.1700
Data Index: 1974012 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.8700. Min Act: -0.1700
Data Index: 5288529 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.8075. Min Act: -0.1700
Data Index: 674395 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.7762. Min Act: -0.1700
Data Index: 5448005 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.7450. Min Act: -0.1700
Data Index: 4078974 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.7450. Min Act: -0.1700
Data Index: 7993184 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.7450. Min Act: -0.1700
Data Index: 2888029 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.7450. Min Act: -0.1700
Data Index: 3457110 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.7137. Min Act: -0.1700
Data Index: 528081 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.7137. Min Act: -0.1700
Data Index: 935157 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.7137. Min Act: -0.1700
Data Index: 1378651 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.6825. Min Act: -0.1700
Data Index: 1359561 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.6200. Min Act: -0.1700
Data Index: 5198416 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.6200. Min Act: -0.1700
Data Index: 735953 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.6200. Min Act: -0.1700
Data Index: 7400215 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.6200. Min Act: -0.1700
Data Index: 2435153 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.5887. Min Act: -0.1700
Data Index: 4518468 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0262. Min Range: -8.0262
Max Act: 7.5887. Min Act: -0.1700
Data Index: 4187802 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19