Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 630 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6852. Min Range: -8.6852
Max Act: 8.6852. Min Act: -0.1700
Data Index: 927717 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6852. Min Range: -8.6852
Max Act: 8.3727. Min Act: -0.1700
Data Index: 1881070 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6852. Min Range: -8.6852
Max Act: 8.3102. Min Act: -0.1700
Data Index: 7889885 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6852. Min Range: -8.6852
Max Act: 8.1852. Min Act: -0.1700
Data Index: 2723492 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6852. Min Range: -8.6852
Max Act: 8.1227. Min Act: -0.1700
Data Index: 402290 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6852. Min Range: -8.6852
Max Act: 8.1227. Min Act: -0.1700
Data Index: 1747302 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6852. Min Range: -8.6852
Max Act: 8.1227. Min Act: -0.1700
Data Index: 8594476 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.9977. Min Act: -0.1700
Data Index: 3645296 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6852. Min Range: -8.6852
Max Act: 8.0602. Min Act: -0.1700
Data Index: 6650141 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6852. Min Range: -8.6852
Max Act: 8.0602. Min Act: -0.1700
Data Index: 8226316 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.8727. Min Act: -0.1700
Data Index: 3109256 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.9352. Min Act: -0.1700
Data Index: 8444910 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.9352. Min Act: -0.1700
Data Index: 8146649 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.8727. Min Act: -0.1700
Data Index: 2664451 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.8727. Min Act: -0.1700
Data Index: 4126200 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.9352. Min Act: -0.1700
Data Index: 8610057 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.8102. Min Act: -0.1700
Data Index: 6086141 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.8102. Min Act: -0.1700
Data Index: 6783007 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.8102. Min Act: -0.1700
Data Index: 7143474 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6852. Min Range: -8.6852
Max Act: 7.8102. Min Act: -0.1700
Data Index: 8527622 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19