Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2308 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.1558. Min Range: -10.1558
Max Act: 10.1558. Min Act: -0.1700
Data Index: 5815549 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1558. Min Range: -10.1558
Max Act: 10.0308. Min Act: -0.1700
Data Index: 1513758 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1558. Min Range: -10.1558
Max Act: 10.0308. Min Act: -0.1693
Data Index: 391584 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1558. Min Range: -10.1558
Max Act: 10.0308. Min Act: -0.1672
Data Index: 4439286 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9683. Min Act: -0.1696
Data Index: 3777600 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9683. Min Act: -0.1635
Data Index: 5499078 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9683. Min Act: -0.1691
Data Index: 4784523 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9683. Min Act: -0.1698
Data Index: 4221582 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9683. Min Act: -0.1686
Data Index: 5807165 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9683. Min Act: -0.1487
Data Index: 5499074 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9683. Min Act: -0.1693
Data Index: 2888750 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1558. Min Range: -10.1558
Max Act: 10.0308. Min Act: -0.1663
Data Index: 5499071 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9058. Min Act: -0.1697
Data Index: 4433246 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9058. Min Act: -0.1699
Data Index: 4483754 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9058. Min Act: -0.1700
Data Index: 226077 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9058. Min Act: -0.1693
Data Index: 1478857 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9058. Min Act: -0.1695
Data Index: 5030430 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9058. Min Act: -0.1700
Data Index: 5124707 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9058. Min Act: -0.1600
Data Index: 5323651 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1558. Min Range: -10.1558
Max Act: 9.9058. Min Act: -0.1683
Data Index: 5375371 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19