Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4034 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.9068. Min Act: -0.1700
Data Index: 1045982 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.8443. Min Act: -0.1700
Data Index: 652159 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.8443. Min Act: -0.1700
Data Index: 6624013 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.8443. Min Act: -0.1700
Data Index: 8663750 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.8130. Min Act: -0.1700
Data Index: 5120057 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7818. Min Act: -0.1700
Data Index: 4204960 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7505. Min Act: -0.1700
Data Index: 728049 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7505. Min Act: -0.1700
Data Index: 3040973 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.6880. Min Act: -0.1700
Data Index: 5093512 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7193. Min Act: -0.1700
Data Index: 5118776 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7193. Min Act: -0.1700
Data Index: 7860371 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7193. Min Act: -0.1700
Data Index: 5813076 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7193. Min Act: -0.1700
Data Index: 8673115 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7193. Min Act: -0.1700
Data Index: 6648868 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7505. Min Act: -0.1700
Data Index: 8639157 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.6880. Min Act: -0.1700
Data Index: 7229689 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.6880. Min Act: -0.1700
Data Index: 1829138 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.6880. Min Act: -0.1700
Data Index: 5705497 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7193. Min Act: -0.1700
Data Index: 2530513 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9068. Min Range: -5.9068
Max Act: 5.7193. Min Act: -0.1700
Data Index: 7972940 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19