Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5551 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.3925. Min Act: -0.1700
Data Index: 4285447 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.3613. Min Act: -0.1700
Data Index: 6156368 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.3613. Min Act: -0.1700
Data Index: 4898360 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.2988. Min Act: -0.1700
Data Index: 4473109 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.2675. Min Act: -0.1700
Data Index: 8826128 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.2675. Min Act: -0.1700
Data Index: 8075296 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.2363. Min Act: -0.1700
Data Index: 125346 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.2363. Min Act: -0.1700
Data Index: 262205 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.2363. Min Act: -0.1700
Data Index: 555479 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.2363. Min Act: -0.1700
Data Index: 7507654 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.2050. Min Act: -0.1700
Data Index: 3888918 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1425. Min Act: -0.1700
Data Index: 2847492 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1425. Min Act: -0.1700
Data Index: 7075616 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1425. Min Act: -0.1700
Data Index: 2662355 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1113. Min Act: -0.1700
Data Index: 7751028 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1113. Min Act: -0.1700
Data Index: 7853768 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1113. Min Act: -0.1700
Data Index: 6493960 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.1113. Min Act: -0.1700
Data Index: 6418479 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.0800. Min Act: -0.1700
Data Index: 2543921 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3925. Min Range: -6.3925
Max Act: 6.0800. Min Act: -0.1700
Data Index: 86468 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19