Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8906. Min Act: -0.1700
Data Index: 8496166 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8430. Min Act: -0.1700
Data Index: 1482045 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8430. Min Act: -0.1700
Data Index: 3055938 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8748. Min Act: -0.1700
Data Index: 6338672 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8430. Min Act: -0.1700
Data Index: 8079296 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8589. Min Act: -0.1700
Data Index: 6784458 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8271. Min Act: -0.1700
Data Index: 4678366 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8271. Min Act: -0.1700
Data Index: 1952527 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8430. Min Act: -0.1700
Data Index: 715328 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8271. Min Act: -0.1700
Data Index: 5122081 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8112. Min Act: -0.1700
Data Index: 2951661 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8271. Min Act: -0.1700
Data Index: 2732044 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8112. Min Act: -0.1700
Data Index: 5414442 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8112. Min Act: -0.1700
Data Index: 8147534 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.8112. Min Act: -0.1700
Data Index: 5438077 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.7953. Min Act: -0.1700
Data Index: 2498330 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.7953. Min Act: -0.1700
Data Index: 2962111 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.7953. Min Act: -0.1700
Data Index: 359020 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.7793. Min Act: -0.1700
Data Index: 513917 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8906. Min Range: -2.8906
Max Act: 2.7953. Min Act: -0.1700
Data Index: 4951606 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19