Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4105 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.8153. Min Act: -0.1700
Data Index: 2036564 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.8153. Min Act: -0.1700
Data Index: 6240657 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.7840. Min Act: -0.1700
Data Index: 6436805 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.6903. Min Act: -0.1700
Data Index: 6050132 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.6590. Min Act: -0.1700
Data Index: 1947755 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.6590. Min Act: -0.1700
Data Index: 8377108 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.6278. Min Act: -0.1700
Data Index: 2332760 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.6278. Min Act: -0.1700
Data Index: 1109684 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.5965. Min Act: -0.1700
Data Index: 884668 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.5965. Min Act: -0.1700
Data Index: 8125434 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.5653. Min Act: -0.1700
Data Index: 1561949 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.5340. Min Act: -0.1700
Data Index: 3487642 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.5028. Min Act: -0.1700
Data Index: 5368468 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.5028. Min Act: -0.1700
Data Index: 8131877 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.5028. Min Act: -0.1700
Data Index: 1957854 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4715. Min Act: -0.1700
Data Index: 5688692 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4403. Min Act: -0.1700
Data Index: 1229700 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4715. Min Act: -0.1700
Data Index: 5324647 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4715. Min Act: -0.1700
Data Index: 8548526 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4715. Min Act: -0.1700
Data Index: 4958319 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19