Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.8764. Min Act: -0.1700
Data Index: 1998322 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.8764. Min Act: -0.1700
Data Index: 8120175 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.8139. Min Act: -0.1700
Data Index: 7296308 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.8139. Min Act: -0.1700
Data Index: 7247627 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.7514. Min Act: -0.1700
Data Index: 7585080 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.5639. Min Act: -0.1700
Data Index: 6563658 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.5014. Min Act: -0.1700
Data Index: 3701934 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.4389. Min Act: -0.1700
Data Index: 4283416 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.4389. Min Act: -0.1700
Data Index: 1606575 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.4389. Min Act: -0.1700
Data Index: 4688221 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.4389. Min Act: -0.1700
Data Index: 7760205 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.3764. Min Act: -0.1700
Data Index: 7361669 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.3764. Min Act: -0.1700
Data Index: 1526975 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.4389. Min Act: -0.1700
Data Index: 5075136 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.3139. Min Act: -0.1700
Data Index: 8471961 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.3139. Min Act: -0.1700
Data Index: 2251342 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.2514. Min Act: -0.1700
Data Index: 8036753 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.1889. Min Act: -0.1700
Data Index: 4632697 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.1264. Min Act: -0.1700
Data Index: 5462673 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8764. Min Range: -10.8764
Max Act: 10.1264. Min Act: -0.1700
Data Index: 2952129 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19