Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 863 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.7767. Min Act: -0.1700
Data Index: 688204 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5733. Min Act: -0.1700
Data Index: 1409433 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5577. Min Act: -0.1700
Data Index: 7440241 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5890. Min Act: -0.1700
Data Index: 5668926 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4481. Min Act: -0.1700
Data Index: 3204352 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4481. Min Act: -0.1700
Data Index: 3863862 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4481. Min Act: -0.1700
Data Index: 8295716 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.3697. Min Act: -0.1700
Data Index: 5732785 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4167. Min Act: -0.1700
Data Index: 8538059 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.3854. Min Act: -0.1700
Data Index: 1712117 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.3854. Min Act: -0.1700
Data Index: 8676552 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4167. Min Act: -0.1700
Data Index: 2601088 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4010. Min Act: -0.1700
Data Index: 3974795 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.3540. Min Act: -0.1700
Data Index: 2330297 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.3540. Min Act: -0.1700
Data Index: 7360130 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.3540. Min Act: -0.1700
Data Index: 6001664 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.3697. Min Act: -0.1700
Data Index: 8536897 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.3540. Min Act: -0.1700
Data Index: 6001665 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.3383. Min Act: -0.1700
Data Index: 7872291 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.3697. Min Act: -0.1700
Data Index: 4577726 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19