Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.6689. Min Act: -0.1700
Data Index: 6625788 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.5752. Min Act: -0.1700
Data Index: 6145840 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.5127. Min Act: -0.1700
Data Index: 4000855 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.5127. Min Act: -0.1700
Data Index: 4562548 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.4814. Min Act: -0.1700
Data Index: 4877964 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.4814. Min Act: -0.1700
Data Index: 7996482 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.4502. Min Act: -0.1700
Data Index: 1450345 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.4814. Min Act: -0.1700
Data Index: 5742477 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.4189. Min Act: -0.1700
Data Index: 1422509 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.4502. Min Act: -0.1700
Data Index: 8149121 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.4189. Min Act: -0.1700
Data Index: 6331758 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.4189. Min Act: -0.1700
Data Index: 1243959 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.4189. Min Act: -0.1700
Data Index: 6958455 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.3877. Min Act: -0.1700
Data Index: 4158468 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.3877. Min Act: -0.1700
Data Index: 614418 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.3877. Min Act: -0.1700
Data Index: 4869556 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.3877. Min Act: -0.1700
Data Index: 5363239 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.3877. Min Act: -0.1700
Data Index: 4833658 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.3877. Min Act: -0.1700
Data Index: 3607434 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6689. Min Range: -5.6689
Max Act: 5.3877. Min Act: -0.1700
Data Index: 5039086 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19