Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.6030. Min Act: -0.1700
Data Index: 348208 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.4899. Min Act: -0.1700
Data Index: 6979687 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.4737. Min Act: -0.1700
Data Index: 4572121 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.4737. Min Act: -0.1700
Data Index: 7703587 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.4249. Min Act: -0.1700
Data Index: 4595646 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3923. Min Act: -0.1700
Data Index: 5236524 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.4086. Min Act: -0.1700
Data Index: 1837291 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.4249. Min Act: -0.1700
Data Index: 7966248 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3759. Min Act: -0.1700
Data Index: 7526390 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3759. Min Act: -0.1700
Data Index: 7084717 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3759. Min Act: -0.1700
Data Index: 8391921 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3923. Min Act: -0.1700
Data Index: 4757446 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3432. Min Act: -0.1700
Data Index: 8268882 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3596. Min Act: -0.1700
Data Index: 1646004 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3432. Min Act: -0.1700
Data Index: 969286 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3268. Min Act: -0.1700
Data Index: 7189129 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3432. Min Act: -0.1700
Data Index: 6289780 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3268. Min Act: -0.1700
Data Index: 6304107 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3268. Min Act: -0.1700
Data Index: 2259411 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6030. Min Range: -2.6030
Max Act: 2.3104. Min Act: -0.1700
Data Index: 1179543 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19