Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1537. Min Range: -4.1537
Max Act: 4.1537. Min Act: -0.1700
Data Index: 4194848 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1537. Min Range: -4.1537
Max Act: 4.1537. Min Act: -0.1700
Data Index: 1217143 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1537. Min Range: -4.1537
Max Act: 4.1537. Min Act: -0.1700
Data Index: 4429117 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1537. Min Range: -4.1537
Max Act: 4.1224. Min Act: -0.1700
Data Index: 4429115 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1537. Min Range: -4.1537
Max Act: 4.0912. Min Act: -0.1700
Data Index: 8054548 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1537. Min Range: -4.1537
Max Act: 4.0599. Min Act: -0.1700
Data Index: 930570 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1537. Min Range: -4.1537
Max Act: 4.0599. Min Act: -0.1700
Data Index: 3365130 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1537. Min Range: -4.1537
Max Act: 4.0286. Min Act: -0.1700
Data Index: 4991935 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1537. Min Range: -4.1537
Max Act: 3.9974. Min Act: -0.1700
Data Index: 4640434 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1537. Min Range: -4.1537
Max Act: 4.0286. Min Act: -0.1700
Data Index: 8419527 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1537. Min Range: -4.1537
Max Act: 4.0286. Min Act: -0.1700
Data Index: 1446499 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1537. Min Range: -4.1537
Max Act: 3.9974. Min Act: -0.1700
Data Index: 598963 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1537. Min Range: -4.1537
Max Act: 3.9661. Min Act: -0.1700
Data Index: 5150883 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1537. Min Range: -4.1537
Max Act: 3.9661. Min Act: -0.1700
Data Index: 5029742 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1537. Min Range: -4.1537
Max Act: 3.9661. Min Act: -0.1700
Data Index: 6658819 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1537. Min Range: -4.1537
Max Act: 3.9661. Min Act: -0.1700
Data Index: 6966174 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1537. Min Range: -4.1537
Max Act: 3.9661. Min Act: -0.1700
Data Index: 7379694 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1537. Min Range: -4.1537
Max Act: 3.9661. Min Act: -0.1700
Data Index: 3726344 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1537. Min Range: -4.1537
Max Act: 3.9661. Min Act: -0.1700
Data Index: 7601011 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1537. Min Range: -4.1537
Max Act: 3.9661. Min Act: -0.1700
Data Index: 3453866 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19