Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0975. Min Range: -6.0975
Max Act: 6.0975. Min Act: -0.1700
Data Index: 1480584 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.9413. Min Act: -0.1700
Data Index: 100791 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.8475. Min Act: -0.1700
Data Index: 6533579 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.7538. Min Act: -0.1700
Data Index: 1094070 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.7538. Min Act: -0.1700
Data Index: 4481469 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.7538. Min Act: -0.1700
Data Index: 1959909 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.7225. Min Act: -0.1700
Data Index: 4797754 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6913. Min Act: -0.1700
Data Index: 1352156 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6913. Min Act: -0.1700
Data Index: 11697 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6913. Min Act: -0.1700
Data Index: 6389465 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6600. Min Act: -0.1700
Data Index: 3569344 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6600. Min Act: -0.1700
Data Index: 7939534 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6600. Min Act: -0.1700
Data Index: 1143816 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6600. Min Act: -0.1700
Data Index: 1174985 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6288. Min Act: -0.1700
Data Index: 3569655 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6288. Min Act: -0.1700
Data Index: 1959910 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6288. Min Act: -0.1700
Data Index: 679773 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6288. Min Act: -0.1700
Data Index: 4153565 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.6288. Min Act: -0.1700
Data Index: 3106941 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0975. Min Range: -6.0975
Max Act: 5.5975. Min Act: -0.1700
Data Index: 2642931 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19