Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 753 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3201. Min Range: -9.3201
Max Act: 9.3201. Min Act: -0.1700
Data Index: 6084061 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.7576. Min Act: -0.1700
Data Index: 5132618 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.5076. Min Act: -0.1635
Data Index: 3132648 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.3826. Min Act: -0.1693
Data Index: 4391980 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.3201. Min Act: -0.1700
Data Index: 2629203 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.2576. Min Act: -0.1700
Data Index: 4560955 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.1326. Min Act: -0.1700
Data Index: 5114864 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.1951. Min Act: -0.1664
Data Index: 2165296 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.2576. Min Act: -0.1700
Data Index: 4422861 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.0701. Min Act: -0.1697
Data Index: 2156690 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3201. Min Range: -9.3201
Max Act: 7.9451. Min Act: -0.1700
Data Index: 5966834 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.0701. Min Act: -0.1700
Data Index: 2168304 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3201. Min Range: -9.3201
Max Act: 8.0076. Min Act: -0.1700
Data Index: 1630770 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3201. Min Range: -9.3201
Max Act: 7.9451. Min Act: -0.1700
Data Index: 7316276 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3201. Min Range: -9.3201
Max Act: 7.9451. Min Act: -0.1700
Data Index: 3892723 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3201. Min Range: -9.3201
Max Act: 7.9451. Min Act: -0.1699
Data Index: 5292156 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3201. Min Range: -9.3201
Max Act: 7.9451. Min Act: -0.1697
Data Index: 3068521 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3201. Min Range: -9.3201
Max Act: 7.8826. Min Act: -0.1700
Data Index: 3919763 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3201. Min Range: -9.3201
Max Act: 7.9451. Min Act: -0.1663
Data Index: 4298313 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3201. Min Range: -9.3201
Max Act: 7.9451. Min Act: -0.1700
Data Index: 2046352 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19