Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0388. Min Range: -6.0388
Max Act: 6.0388. Min Act: -0.1700
Data Index: 4390486 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.9138. Min Act: -0.1700
Data Index: 8101612 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.8513. Min Act: -0.1700
Data Index: 7511567 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.8513. Min Act: -0.1700
Data Index: 2729790 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.8201. Min Act: -0.1700
Data Index: 6203471 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.8513. Min Act: -0.1700
Data Index: 1813732 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.8201. Min Act: -0.1700
Data Index: 7937730 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.7888. Min Act: -0.1700
Data Index: 5057761 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.7576. Min Act: -0.1700
Data Index: 330250 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.7576. Min Act: -0.1700
Data Index: 1801669 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.7576. Min Act: -0.1700
Data Index: 4562427 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.7576. Min Act: -0.1700
Data Index: 7254622 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.7576. Min Act: -0.1700
Data Index: 5571692 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.7263. Min Act: -0.1700
Data Index: 6812475 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.7263. Min Act: -0.1700
Data Index: 6400401 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.7263. Min Act: -0.1700
Data Index: 603060 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.6638. Min Act: -0.1700
Data Index: 7264551 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.6638. Min Act: -0.1700
Data Index: 3316098 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.6951. Min Act: -0.1700
Data Index: 4232742 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0388. Min Range: -6.0388
Max Act: 5.6326. Min Act: -0.1700
Data Index: 5109467 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19