Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2743 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1749. Min Range: -8.1749
Max Act: 8.1749. Min Act: -0.1700
Data Index: 2729901 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.9874. Min Act: -0.1700
Data Index: 8811475 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.9249. Min Act: -0.1700
Data Index: 3464995 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.9562. Min Act: -0.1700
Data Index: 1447234 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.9249. Min Act: -0.1700
Data Index: 6156881 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.9249. Min Act: -0.1700
Data Index: 4696488 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.8624. Min Act: -0.1700
Data Index: 2590343 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.8312. Min Act: -0.1700
Data Index: 5884049 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.8624. Min Act: -0.1700
Data Index: 4760792 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7999. Min Act: -0.1700
Data Index: 2204254 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7999. Min Act: -0.1700
Data Index: 126525 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7687. Min Act: -0.1700
Data Index: 2447171 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7687. Min Act: -0.1700
Data Index: 6759271 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7687. Min Act: -0.1700
Data Index: 1347324 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7687. Min Act: -0.1700
Data Index: 4228818 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7687. Min Act: -0.1700
Data Index: 6877514 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7062. Min Act: -0.1700
Data Index: 2227591 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7687. Min Act: -0.1700
Data Index: 218578 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7062. Min Act: -0.1700
Data Index: 1987919 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1749. Min Range: -8.1749
Max Act: 7.7374. Min Act: -0.1700
Data Index: 6785531 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19