Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 909 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0757. Min Range: -9.0757
Max Act: 9.0757. Min Act: -0.1700
Data Index: 5794314 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.7007. Min Act: -0.1700
Data Index: 8555560 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.7007. Min Act: -0.1700
Data Index: 373480 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.7007. Min Act: -0.1700
Data Index: 2040748 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.7007. Min Act: -0.1700
Data Index: 7161069 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.7007. Min Act: -0.1700
Data Index: 7721260 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.6382. Min Act: -0.1700
Data Index: 6233188 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.6382. Min Act: -0.1700
Data Index: 1021749 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.6382. Min Act: -0.1700
Data Index: 7965769 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5757. Min Act: -0.1700
Data Index: 6654611 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5757. Min Act: -0.1700
Data Index: 6521688 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5757. Min Act: -0.1700
Data Index: 6360165 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5757. Min Act: -0.1700
Data Index: 8499495 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5757. Min Act: -0.1700
Data Index: 103521 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5757. Min Act: -0.1700
Data Index: 412999 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5132. Min Act: -0.1700
Data Index: 13884 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5757. Min Act: -0.1700
Data Index: 2355640 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5757. Min Act: -0.1700
Data Index: 7017232 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5757. Min Act: -0.1700
Data Index: 507917 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0757. Min Range: -9.0757
Max Act: 8.5132. Min Act: -0.1700
Data Index: 972541 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19