Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.3634. Min Act: -0.1700
Data Index: 6135224 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.3634. Min Act: -0.1700
Data Index: 5230887 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.2384. Min Act: -0.1700
Data Index: 5535307 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.1759. Min Act: -0.1700
Data Index: 5129350 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.1759. Min Act: -0.1700
Data Index: 4838078 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.1446. Min Act: -0.1700
Data Index: 127899 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.1446. Min Act: -0.1700
Data Index: 8069330 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.1134. Min Act: -0.1700
Data Index: 6795579 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.1134. Min Act: -0.1700
Data Index: 6955342 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.0821. Min Act: -0.1700
Data Index: 7417376 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.0509. Min Act: -0.1700
Data Index: 157488 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.0196. Min Act: -0.1700
Data Index: 7333698 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.0196. Min Act: -0.1700
Data Index: 7177550 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.0196. Min Act: -0.1700
Data Index: 8466721 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9884. Min Act: -0.1700
Data Index: 8590994 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9884. Min Act: -0.1700
Data Index: 1263312 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9884. Min Act: -0.1700
Data Index: 1321076 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9571. Min Act: -0.1700
Data Index: 7667082 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9571. Min Act: -0.1700
Data Index: 2687155 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9571. Min Act: -0.1700
Data Index: 8458257 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19