Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5379 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.1434. Min Act: -0.1700
Data Index: 6057323 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.1747. Min Act: -0.1700
Data Index: 2300444 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.1434. Min Act: -0.1700
Data Index: 5781568 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.1434. Min Act: -0.1700
Data Index: 1200966 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0809. Min Act: -0.1700
Data Index: 4641708 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0809. Min Act: -0.1700
Data Index: 6865930 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0497. Min Act: -0.1700
Data Index: 4216817 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 8249340 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0497. Min Act: -0.1700
Data Index: 3530235 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 4750713 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 2843374 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 3137470 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 1398963 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 7461831 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 2448385 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 3218939 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 3333856 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 2628726 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1747. Min Range: -7.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 3717100 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1747. Min Range: -7.1747
Max Act: 6.9872. Min Act: -0.1700
Data Index: 4465022 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19