Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 947 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0065. Min Range: -8.0065
Max Act: 8.0065. Min Act: -0.1700
Data Index: 1132524 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0065. Min Range: -8.0065
Max Act: 7.4752. Min Act: -0.1700
Data Index: 278528 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0065. Min Range: -8.0065
Max Act: 7.3815. Min Act: -0.1700
Data Index: 5743104 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0065. Min Range: -8.0065
Max Act: 7.3502. Min Act: -0.1700
Data Index: 677111 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0065. Min Range: -8.0065
Max Act: 7.2565. Min Act: -0.1700
Data Index: 8480546 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0065. Min Range: -8.0065
Max Act: 7.2252. Min Act: -0.1700
Data Index: 7204839 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0065. Min Range: -8.0065
Max Act: 7.1940. Min Act: -0.1700
Data Index: 3197982 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0065. Min Range: -8.0065
Max Act: 7.1315. Min Act: -0.1700
Data Index: 2535714 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0065. Min Range: -8.0065
Max Act: 7.1002. Min Act: -0.1700
Data Index: 3609915 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0065. Min Range: -8.0065
Max Act: 7.0690. Min Act: -0.1700
Data Index: 3779054 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0065. Min Range: -8.0065
Max Act: 7.0690. Min Act: -0.1700
Data Index: 4205344 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0065. Min Range: -8.0065
Max Act: 6.9752. Min Act: -0.1700
Data Index: 5531296 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0065. Min Range: -8.0065
Max Act: 6.9440. Min Act: -0.1700
Data Index: 2044434 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0065. Min Range: -8.0065
Max Act: 6.9752. Min Act: -0.1700
Data Index: 229871 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0065. Min Range: -8.0065
Max Act: 6.9127. Min Act: -0.1700
Data Index: 5760412 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0065. Min Range: -8.0065
Max Act: 6.9127. Min Act: -0.1700
Data Index: 6787090 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0065. Min Range: -8.0065
Max Act: 6.9127. Min Act: -0.1700
Data Index: 8734864 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0065. Min Range: -8.0065
Max Act: 6.9127. Min Act: -0.1700
Data Index: 7231447 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0065. Min Range: -8.0065
Max Act: 6.9127. Min Act: -0.1700
Data Index: 3865673 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0065. Min Range: -8.0065
Max Act: 6.8815. Min Act: -0.1700
Data Index: 5148602 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19