Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3915 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.5342. Min Act: -0.1700
Data Index: 6149780 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.5342. Min Act: -0.1700
Data Index: 647228 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.5029. Min Act: -0.1700
Data Index: 4752674 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.4404. Min Act: -0.1700
Data Index: 7626643 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.3779. Min Act: -0.1700
Data Index: 7495665 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.3466. Min Act: -0.1700
Data Index: 654414 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.3466. Min Act: -0.1700
Data Index: 7689598 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.3154. Min Act: -0.1700
Data Index: 6149781 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.3466. Min Act: -0.1700
Data Index: 6790293 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.2841. Min Act: -0.1700
Data Index: 204422 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.1904. Min Act: -0.1700
Data Index: 3439790 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.1904. Min Act: -0.1700
Data Index: 7183757 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.1904. Min Act: -0.1700
Data Index: 5544298 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.1904. Min Act: -0.1700
Data Index: 2587913 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.1591. Min Act: -0.1700
Data Index: 4322633 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.1591. Min Act: -0.1700
Data Index: 1485808 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.1591. Min Act: -0.1700
Data Index: 5291607 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.1591. Min Act: -0.1700
Data Index: 952573 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.1904. Min Act: -0.1700
Data Index: 4211652 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5342. Min Range: -4.5342
Max Act: 4.1591. Min Act: -0.1700
Data Index: 664121 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19