Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.9178. Min Act: -0.1700
Data Index: 7608564 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.8865. Min Act: -0.1700
Data Index: 1452417 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.8240. Min Act: -0.1700
Data Index: 5376295 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.7302. Min Act: -0.1700
Data Index: 7674225 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6989. Min Act: -0.1700
Data Index: 3766739 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6989. Min Act: -0.1700
Data Index: 4401648 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6989. Min Act: -0.1700
Data Index: 6162423 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6676. Min Act: -0.1700
Data Index: 2109551 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6676. Min Act: -0.1700
Data Index: 3604187 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6676. Min Act: -0.1700
Data Index: 4333228 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6676. Min Act: -0.1700
Data Index: 5034536 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6363. Min Act: -0.1700
Data Index: 351220 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6676. Min Act: -0.1700
Data Index: 3242129 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6676. Min Act: -0.1700
Data Index: 4627406 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6363. Min Act: -0.1700
Data Index: 2019455 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6363. Min Act: -0.1700
Data Index: 667235 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6363. Min Act: -0.1700
Data Index: 5888514 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6050. Min Act: -0.1700
Data Index: 7929460 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6050. Min Act: -0.1700
Data Index: 7253576 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9178. Min Range: -3.9178
Max Act: 3.6050. Min Act: -0.1700
Data Index: 5767682 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19