Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3831. Min Range: -7.3831
Max Act: 7.3831. Min Act: -0.1700
Data Index: 7740635 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3831. Min Range: -7.3831
Max Act: 7.3518. Min Act: -0.1700
Data Index: 2388372 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3831. Min Range: -7.3831
Max Act: 7.3206. Min Act: -0.1700
Data Index: 405498 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3831. Min Range: -7.3831
Max Act: 7.3206. Min Act: -0.1700
Data Index: 6145132 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3831. Min Range: -7.3831
Max Act: 7.3206. Min Act: -0.1700
Data Index: 6145133 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3831. Min Range: -7.3831
Max Act: 7.2893. Min Act: -0.1700
Data Index: 677220 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3831. Min Range: -7.3831
Max Act: 7.1956. Min Act: -0.1700
Data Index: 814961 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3831. Min Range: -7.3831
Max Act: 7.1018. Min Act: -0.1700
Data Index: 1357003 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3831. Min Range: -7.3831
Max Act: 7.0081. Min Act: -0.1700
Data Index: 436459 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.9768. Min Act: -0.1700
Data Index: 7532951 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.9768. Min Act: -0.1700
Data Index: 4266552 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.9768. Min Act: -0.1700
Data Index: 4330795 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.9456. Min Act: -0.1700
Data Index: 1499564 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.9768. Min Act: -0.1700
Data Index: 7068817 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.9143. Min Act: -0.1700
Data Index: 539181 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.9143. Min Act: -0.1700
Data Index: 1302769 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.9143. Min Act: -0.1700
Data Index: 7907577 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.8831. Min Act: -0.1700
Data Index: 5660939 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.8206. Min Act: -0.1700
Data Index: 7011779 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3831. Min Range: -7.3831
Max Act: 6.8831. Min Act: -0.1700
Data Index: 5730344 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19