Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3252. Min Range: -7.3252
Max Act: 7.3252. Min Act: -0.1700
Data Index: 3246503 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3252. Min Range: -7.3252
Max Act: 7.2627. Min Act: -0.1700
Data Index: 3558663 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3252. Min Range: -7.3252
Max Act: 7.1689. Min Act: -0.1700
Data Index: 7915735 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3252. Min Range: -7.3252
Max Act: 7.1064. Min Act: -0.1700
Data Index: 5910314 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3252. Min Range: -7.3252
Max Act: 7.1064. Min Act: -0.1700
Data Index: 7515483 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3252. Min Range: -7.3252
Max Act: 7.0127. Min Act: -0.1700
Data Index: 2722803 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.9814. Min Act: -0.1700
Data Index: 6743903 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.9814. Min Act: -0.1700
Data Index: 7062594 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.9814. Min Act: -0.1700
Data Index: 3223238 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.9502. Min Act: -0.1700
Data Index: 2462248 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.9502. Min Act: -0.1700
Data Index: 3256129 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.9189. Min Act: -0.1700
Data Index: 3648505 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.9189. Min Act: -0.1700
Data Index: 4809106 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.8877. Min Act: -0.1700
Data Index: 2864614 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.8877. Min Act: -0.1700
Data Index: 2579962 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.8877. Min Act: -0.1700
Data Index: 541006 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.8564. Min Act: -0.1700
Data Index: 7369482 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.8564. Min Act: -0.1700
Data Index: 3190589 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.8564. Min Act: -0.1700
Data Index: 8649012 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3252. Min Range: -7.3252
Max Act: 6.7939. Min Act: -0.1700
Data Index: 4360185 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19