Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0811. Min Range: -4.0811
Max Act: 4.0811. Min Act: -0.1700
Data Index: 1100850 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0811. Min Range: -4.0811
Max Act: 4.0186. Min Act: -0.1700
Data Index: 6818685 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.9561. Min Act: -0.1700
Data Index: 6818690 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.9561. Min Act: -0.1700
Data Index: 6818687 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.9561. Min Act: -0.1700
Data Index: 1328726 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.8623. Min Act: -0.1700
Data Index: 6398436 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.8310. Min Act: -0.1700
Data Index: 5788807 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.8310. Min Act: -0.1700
Data Index: 6818684 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.8310. Min Act: -0.1698
Data Index: 975 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.8310. Min Act: -0.1700
Data Index: 8485083 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7998. Min Act: -0.1700
Data Index: 7971797 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7685. Min Act: -0.1700
Data Index: 4059650 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7685. Min Act: -0.1700
Data Index: 5127810 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7372. Min Act: -0.1700
Data Index: 2069892 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7372. Min Act: -0.1700
Data Index: 2642960 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7059. Min Act: -0.1700
Data Index: 6885834 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7372. Min Act: -0.1700
Data Index: 6818681 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7059. Min Act: -0.1700
Data Index: 6818686 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.7059. Min Act: -0.1700
Data Index: 923304 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0811. Min Range: -4.0811
Max Act: 3.6433. Min Act: -0.1700
Data Index: 5557393 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19