Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6095 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.8440. Min Act: -0.1700
Data Index: 7299462 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.8440. Min Act: -0.1700
Data Index: 3972971 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.7502. Min Act: -0.1700
Data Index: 8167639 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.7502. Min Act: -0.1700
Data Index: 8080181 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.6252. Min Act: -0.1700
Data Index: 5816797 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.5940. Min Act: -0.1700
Data Index: 3063876 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.5940. Min Act: -0.1700
Data Index: 2589142 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.5315. Min Act: -0.1700
Data Index: 1475256 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.5315. Min Act: -0.1700
Data Index: 6738952 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.5002. Min Act: -0.1700
Data Index: 5899666 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.5002. Min Act: -0.1700
Data Index: 4112807 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.4377. Min Act: -0.1700
Data Index: 5451621 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.4690. Min Act: -0.1700
Data Index: 4750512 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.4377. Min Act: -0.1700
Data Index: 6255106 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.4065. Min Act: -0.1700
Data Index: 6124548 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.3752. Min Act: -0.1700
Data Index: 1070959 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.4065. Min Act: -0.1700
Data Index: 5193695 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.3127. Min Act: -0.1700
Data Index: 699955 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.3127. Min Act: -0.1700
Data Index: 8368692 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.3127. Min Act: -0.1700
Data Index: 7229719 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19