Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1845 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0774. Min Range: -6.0774
Max Act: 6.0774. Min Act: -0.1700
Data Index: 114599 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0774. Min Range: -6.0774
Max Act: 6.0462. Min Act: -0.1700
Data Index: 4979291 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.8899. Min Act: -0.1700
Data Index: 885714 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7649. Min Act: -0.1700
Data Index: 5199584 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.8274. Min Act: -0.1700
Data Index: 5721530 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.8274. Min Act: -0.1700
Data Index: 996498 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7337. Min Act: -0.1700
Data Index: 3288477 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7649. Min Act: -0.1700
Data Index: 3840479 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7962. Min Act: -0.1700
Data Index: 7122708 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7649. Min Act: -0.1700
Data Index: 200286 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.6712. Min Act: -0.1700
Data Index: 155717 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7024. Min Act: -0.1700
Data Index: 3454905 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7649. Min Act: -0.1700
Data Index: 5718683 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7024. Min Act: -0.1700
Data Index: 4887167 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7024. Min Act: -0.1700
Data Index: 2334937 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7024. Min Act: -0.1700
Data Index: 734044 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.6712. Min Act: -0.1700
Data Index: 7808476 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.6712. Min Act: -0.1700
Data Index: 2855946 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.6712. Min Act: -0.1700
Data Index: 960044 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0774. Min Range: -6.0774
Max Act: 5.7337. Min Act: -0.1700
Data Index: 955285 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19