Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1669 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.6991. Min Act: -0.1700
Data Index: 1438996 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.6366. Min Act: -0.1700
Data Index: 7499370 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.5116. Min Act: -0.1700
Data Index: 3944215 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.1991. Min Act: -0.1700
Data Index: 6543361 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.2616. Min Act: -0.1700
Data Index: 3451151 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.2616. Min Act: -0.1700
Data Index: 237590 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.2616. Min Act: -0.1700
Data Index: 3540028 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.1991. Min Act: -0.1700
Data Index: 4358249 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.1366. Min Act: -0.1700
Data Index: 1086018 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.1678. Min Act: -0.1699
Data Index: 1782328 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.1366. Min Act: -0.1700
Data Index: 7813301 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.1053. Min Act: -0.1700
Data Index: 8215036 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.0428. Min Act: -0.1700
Data Index: 903449 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.0428. Min Act: -0.1700
Data Index: 462281 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.0428. Min Act: -0.1700
Data Index: 1065190 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.0741. Min Act: -0.1700
Data Index: 2764134 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.0428. Min Act: -0.1699
Data Index: 8213901 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.0741. Min Act: -0.1700
Data Index: 207132 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.0428. Min Act: -0.1700
Data Index: 4674586 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6991. Min Range: -7.6991
Max Act: 7.0428. Min Act: -0.1700
Data Index: 1381874 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19