Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2590. Min Range: -5.2590
Max Act: 5.2590. Min Act: -0.1700
Data Index: 8310677 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9778. Min Act: -0.1700
Data Index: 3563791 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.9153. Min Act: -0.1700
Data Index: 2181141 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8840. Min Act: -0.1700
Data Index: 6810269 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8840. Min Act: -0.1700
Data Index: 768152 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8840. Min Act: -0.1700
Data Index: 2277362 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8528. Min Act: -0.1700
Data Index: 6774723 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8215. Min Act: -0.1700
Data Index: 1442837 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8215. Min Act: -0.1700
Data Index: 5999008 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8215. Min Act: -0.1700
Data Index: 6774727 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8528. Min Act: -0.1700
Data Index: 1709131 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8215. Min Act: -0.1700
Data Index: 883734 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8528. Min Act: -0.1700
Data Index: 1425491 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8215. Min Act: -0.1700
Data Index: 4306135 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.7590. Min Act: -0.1700
Data Index: 1174447 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8215. Min Act: -0.1700
Data Index: 3729222 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.8215. Min Act: -0.1700
Data Index: 6527328 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.7903. Min Act: -0.1700
Data Index: 7074769 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.7903. Min Act: -0.1700
Data Index: 768145 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2590. Min Range: -5.2590
Max Act: 4.7590. Min Act: -0.1700
Data Index: 2204462 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19