Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5168 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2252. Min Range: -7.2252
Max Act: 7.2252. Min Act: -0.1700
Data Index: 1410158 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2252. Min Range: -7.2252
Max Act: 7.0690. Min Act: -0.1700
Data Index: 992205 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.9752. Min Act: -0.1700
Data Index: 13250 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.9440. Min Act: -0.1700
Data Index: 3291439 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.8815. Min Act: -0.1700
Data Index: 1741314 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.8815. Min Act: -0.1700
Data Index: 3965606 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.8502. Min Act: -0.1700
Data Index: 6780493 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.8190. Min Act: -0.1700
Data Index: 8493627 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.7877. Min Act: -0.1700
Data Index: 7847012 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.7877. Min Act: -0.1700
Data Index: 4617113 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.7877. Min Act: -0.1700
Data Index: 6550031 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.8190. Min Act: -0.1700
Data Index: 2979584 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.7877. Min Act: -0.1700
Data Index: 7305323 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.8190. Min Act: -0.1700
Data Index: 3408158 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.7877. Min Act: -0.1700
Data Index: 4586684 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.7565. Min Act: -0.1700
Data Index: 1277072 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.7565. Min Act: -0.1700
Data Index: 6848507 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.7565. Min Act: -0.1700
Data Index: 3240231 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.7252. Min Act: -0.1700
Data Index: 4939963 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2252. Min Range: -7.2252
Max Act: 6.7565. Min Act: -0.1700
Data Index: 5479077 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19