Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1083 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1452. Min Act: -0.1677
Data Index: 6780954 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1540. Min Act: -0.1661
Data Index: 2781164 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1189. Min Act: -0.1682
Data Index: 5914798 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1189. Min Act: -0.1696
Data Index: 3873589 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1189. Min Act: -0.1679
Data Index: 5918593 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1189. Min Act: -0.1697
Data Index: 2297039 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.0926. Min Act: -0.1669
Data Index: 8501239 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1101. Min Act: -0.1681
Data Index: 4756683 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1013. Min Act: -0.1630
Data Index: 999106 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1013. Min Act: -0.1698
Data Index: 7058514 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1013. Min Act: -0.1691
Data Index: 7011547 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.0838. Min Act: -0.1669
Data Index: 3662931 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.1013. Min Act: -0.1700
Data Index: 3312158 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.0926. Min Act: -0.1700
Data Index: 8537783 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.0838. Min Act: -0.1700
Data Index: 6379117 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.0926. Min Act: -0.1700
Data Index: 7366853 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.0751. Min Act: -0.1667
Data Index: 7758983 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.0838. Min Act: -0.1699
Data Index: 5188956 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.0751. Min Act: -0.1654
Data Index: 2379590 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1540. Min Range: -1.1540
Max Act: 1.0838. Min Act: -0.1693
Data Index: 884410 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19