Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4049 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.3613. Min Act: -0.1700
Data Index: 432132 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.2988. Min Act: -0.1700
Data Index: 2584436 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.2363. Min Act: -0.1700
Data Index: 7204857 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.2363. Min Act: -0.1700
Data Index: 7979455 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.1113. Min Act: -0.1700
Data Index: 3542304 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.1738. Min Act: -0.1700
Data Index: 8163229 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.1113. Min Act: -0.1700
Data Index: 2594110 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.1113. Min Act: -0.1700
Data Index: 1524442 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.1113. Min Act: -0.1700
Data Index: 8607760 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.1113. Min Act: -0.1700
Data Index: 1961149 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.1113. Min Act: -0.1700
Data Index: 2835807 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.0488. Min Act: -0.1700
Data Index: 6071649 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.0488. Min Act: -0.1700
Data Index: 5115753 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3613. Min Range: -10.3613
Max Act: 10.0488. Min Act: -0.1700
Data Index: 1544998 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3613. Min Range: -10.3613
Max Act: 9.9863. Min Act: -0.1700
Data Index: 6079173 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3613. Min Range: -10.3613
Max Act: 9.9863. Min Act: -0.1700
Data Index: 5220092 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3613. Min Range: -10.3613
Max Act: 9.9863. Min Act: -0.1700
Data Index: 3568392 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3613. Min Range: -10.3613
Max Act: 9.9863. Min Act: -0.1700
Data Index: 5853329 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3613. Min Range: -10.3613
Max Act: 9.9238. Min Act: -0.1700
Data Index: 2075918 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3613. Min Range: -10.3613
Max Act: 9.9238. Min Act: -0.1700
Data Index: 8123169 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19