Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 202 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2840. Min Range: -8.2840
Max Act: 8.2840. Min Act: -0.1700
Data Index: 5688664 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2840. Min Range: -8.2840
Max Act: 8.0965. Min Act: -0.1700
Data Index: 5507947 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.9090. Min Act: -0.1700
Data Index: 1362659 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.8465. Min Act: -0.1700
Data Index: 4508753 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.7840. Min Act: -0.1700
Data Index: 1669470 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.9090. Min Act: -0.1700
Data Index: 4238699 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.7840. Min Act: -0.1700
Data Index: 3250206 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.7840. Min Act: -0.1700
Data Index: 1565401 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.7840. Min Act: -0.1698
Data Index: 8317154 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.7215. Min Act: -0.1700
Data Index: 5364558 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.7840. Min Act: -0.1700
Data Index: 4357411 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.6590. Min Act: -0.1700
Data Index: 1519876 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.6590. Min Act: -0.1700
Data Index: 2918003 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.6590. Min Act: -0.1700
Data Index: 4441457 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.6590. Min Act: -0.1700
Data Index: 1968142 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.6590. Min Act: -0.1700
Data Index: 4644641 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.5965. Min Act: -0.1700
Data Index: 700895 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.5965. Min Act: -0.1700
Data Index: 5937509 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.6590. Min Act: -0.1700
Data Index: 4598770 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2840. Min Range: -8.2840
Max Act: 7.5340. Min Act: -0.1700
Data Index: 2501418 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19