Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4976 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.7467. Min Act: -0.1700
Data Index: 152259 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.7467. Min Act: -0.1700
Data Index: 8507632 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6841. Min Act: -0.1700
Data Index: 5694326 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6841. Min Act: -0.1700
Data Index: 3182846 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6841. Min Act: -0.1700
Data Index: 3987965 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6685. Min Act: -0.1700
Data Index: 4821134 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6685. Min Act: -0.1700
Data Index: 4821325 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6685. Min Act: -0.1700
Data Index: 4821127 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6685. Min Act: -0.1700
Data Index: 7736371 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6528. Min Act: -0.1700
Data Index: 1338676 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6528. Min Act: -0.1700
Data Index: 6792604 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6372. Min Act: -0.1700
Data Index: 893972 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6528. Min Act: -0.1700
Data Index: 4586543 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6372. Min Act: -0.1700
Data Index: 8821038 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6215. Min Act: -0.1700
Data Index: 840461 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6372. Min Act: -0.1700
Data Index: 893982 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6372. Min Act: -0.1700
Data Index: 3816752 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6215. Min Act: -0.1700
Data Index: 1783906 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6215. Min Act: -0.1700
Data Index: 3996186 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7467. Min Range: -3.7467
Max Act: 3.6215. Min Act: -0.1700
Data Index: 781103 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19