Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.9780. Min Act: -0.1700
Data Index: 6533370 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.8829. Min Act: -0.1700
Data Index: 1559993 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.8988. Min Act: -0.1700
Data Index: 2942647 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.8829. Min Act: -0.1700
Data Index: 3117736 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.8353. Min Act: -0.1700
Data Index: 6623424 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.8194. Min Act: -0.1700
Data Index: 7426980 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.8035. Min Act: -0.1700
Data Index: 5567068 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7875. Min Act: -0.1700
Data Index: 5819605 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7875. Min Act: -0.1700
Data Index: 4639711 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7716. Min Act: -0.1700
Data Index: 6950404 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7556. Min Act: -0.1700
Data Index: 8367867 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7716. Min Act: -0.1700
Data Index: 4781151 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7556. Min Act: -0.1700
Data Index: 2748313 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7716. Min Act: -0.1700
Data Index: 4653335 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7556. Min Act: -0.1700
Data Index: 1767422 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7716. Min Act: -0.1700
Data Index: 5474957 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7397. Min Act: -0.1700
Data Index: 115510 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.8035. Min Act: -0.1700
Data Index: 1574865 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7556. Min Act: -0.1700
Data Index: 1567131 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9780. Min Range: -2.9780
Max Act: 2.7556. Min Act: -0.1700
Data Index: 542302 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19