Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3712. Min Range: -10.3712
Max Act: 10.3712. Min Act: -0.1700
Data Index: 7130829 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3712. Min Range: -10.3712
Max Act: 10.3087. Min Act: -0.1700
Data Index: 7580513 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3712. Min Range: -10.3712
Max Act: 10.3087. Min Act: -0.1700
Data Index: 3813225 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3712. Min Range: -10.3712
Max Act: 10.2462. Min Act: -0.1700
Data Index: 1562048 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3712. Min Range: -10.3712
Max Act: 10.2462. Min Act: -0.1700
Data Index: 3986844 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9962. Min Act: -0.1700
Data Index: 8605165 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9962. Min Act: -0.1700
Data Index: 5487638 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9337. Min Act: -0.1700
Data Index: 5471939 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9962. Min Act: -0.1700
Data Index: 7068349 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9962. Min Act: -0.1700
Data Index: 545128 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9337. Min Act: -0.1700
Data Index: 8365448 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.8712. Min Act: -0.1700
Data Index: 5485408 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9337. Min Act: -0.1700
Data Index: 1775370 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9337. Min Act: -0.1700
Data Index: 3572528 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9337. Min Act: -0.1700
Data Index: 5984819 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9337. Min Act: -0.1700
Data Index: 4032659 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.8087. Min Act: -0.1700
Data Index: 1499896 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.8712. Min Act: -0.1700
Data Index: 2904380 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.8712. Min Act: -0.1700
Data Index: 4556920 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3712. Min Range: -10.3712
Max Act: 9.9337. Min Act: -0.1700
Data Index: 8128152 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19