Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2714 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0376. Min Range: -6.0376
Max Act: 6.0376. Min Act: -0.1700
Data Index: 2660479 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.9751. Min Act: -0.1700
Data Index: 6093850 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.8501. Min Act: -0.1700
Data Index: 5911428 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.9126. Min Act: -0.1700
Data Index: 4255865 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.8189. Min Act: -0.1700
Data Index: 587072 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.8189. Min Act: -0.1700
Data Index: 3454847 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.8189. Min Act: -0.1700
Data Index: 7822845 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.8501. Min Act: -0.1700
Data Index: 7461436 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.7564. Min Act: -0.1700
Data Index: 766277 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.7564. Min Act: -0.1700
Data Index: 5056972 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.7251. Min Act: -0.1700
Data Index: 1795957 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.7251. Min Act: -0.1700
Data Index: 1041877 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.6939. Min Act: -0.1700
Data Index: 8208193 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.6626. Min Act: -0.1700
Data Index: 6209757 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.6314. Min Act: -0.1700
Data Index: 6656359 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.6626. Min Act: -0.1700
Data Index: 1220561 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.6626. Min Act: -0.1700
Data Index: 6474283 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.6001. Min Act: -0.1700
Data Index: 6531391 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.6001. Min Act: -0.1700
Data Index: 6729046 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0376. Min Range: -6.0376
Max Act: 5.6314. Min Act: -0.1700
Data Index: 5153056 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19