Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6255 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.9182. Min Act: -0.1700
Data Index: 4877627 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.7307. Min Act: -0.1700
Data Index: 3480136 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.5432. Min Act: -0.1700
Data Index: 5273036 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.3869. Min Act: -0.1700
Data Index: 3908379 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.3869. Min Act: -0.1700
Data Index: 122885 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.3557. Min Act: -0.1700
Data Index: 336033 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.2619. Min Act: -0.1700
Data Index: 5532599 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.1994. Min Act: -0.1700
Data Index: 1615990 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.1682. Min Act: -0.1700
Data Index: 988578 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.1682. Min Act: -0.1700
Data Index: 2790711 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.0744. Min Act: -0.1700
Data Index: 3340331 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.1057. Min Act: -0.1700
Data Index: 8129242 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.0432. Min Act: -0.1700
Data Index: 3301821 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.0432. Min Act: -0.1700
Data Index: 5742155 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.0432. Min Act: -0.1700
Data Index: 5756199 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.0119. Min Act: -0.1700
Data Index: 6867003 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9182. Min Range: -8.9182
Max Act: 8.0119. Min Act: -0.1700
Data Index: 4514693 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9182. Min Range: -8.9182
Max Act: 7.9807. Min Act: -0.1700
Data Index: 8282810 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9182. Min Range: -8.9182
Max Act: 7.9807. Min Act: -0.1700
Data Index: 3821992 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9182. Min Range: -8.9182
Max Act: 7.9494. Min Act: -0.1700
Data Index: 7286824 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19