Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3743 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.9732. Min Act: -0.1700
Data Index: 4989489 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.8169. Min Act: -0.1700
Data Index: 8522970 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.7230. Min Act: -0.1700
Data Index: 3545549 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.7074. Min Act: -0.1700
Data Index: 3255993 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.7230. Min Act: -0.1700
Data Index: 3055235 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.6761. Min Act: -0.1700
Data Index: 6090988 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.6917. Min Act: -0.1700
Data Index: 1006067 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.6605. Min Act: -0.1700
Data Index: 2518176 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.6605. Min Act: -0.1700
Data Index: 314776 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.6448. Min Act: -0.1700
Data Index: 3778013 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.6448. Min Act: -0.1700
Data Index: 8195944 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.6292. Min Act: -0.1700
Data Index: 4994385 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.5979. Min Act: -0.1700
Data Index: 314765 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.5822. Min Act: -0.1700
Data Index: 7104976 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.5665. Min Act: -0.1700
Data Index: 7267938 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.5196. Min Act: -0.1700
Data Index: 6128648 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.5352. Min Act: -0.1700
Data Index: 6863164 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.5352. Min Act: -0.1700
Data Index: 2019153 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.5039. Min Act: -0.1700
Data Index: 314766 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9732. Min Range: -3.9732
Max Act: 3.5196. Min Act: -0.1700
Data Index: 6451605 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19