Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5355 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0509. Min Range: -7.0509
Max Act: 7.0509. Min Act: -0.1700
Data Index: 8208697 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.8322. Min Act: -0.1700
Data Index: 5804555 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.7384. Min Act: -0.1700
Data Index: 4280551 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.7072. Min Act: -0.1700
Data Index: 7324864 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.7072. Min Act: -0.1700
Data Index: 7599795 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6759. Min Act: -0.1700
Data Index: 6000212 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6447. Min Act: -0.1700
Data Index: 8593463 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6447. Min Act: -0.1700
Data Index: 2031319 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.6134. Min Act: -0.1700
Data Index: 4383127 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.5822. Min Act: -0.1700
Data Index: 159520 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.5822. Min Act: -0.1700
Data Index: 6059143 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.5509. Min Act: -0.1700
Data Index: 6313157 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.5509. Min Act: -0.1700
Data Index: 4117720 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.5509. Min Act: -0.1700
Data Index: 5454126 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.5197. Min Act: -0.1700
Data Index: 1440321 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.5197. Min Act: -0.1700
Data Index: 7653332 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.4884. Min Act: -0.1700
Data Index: 8466356 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.4884. Min Act: -0.1700
Data Index: 4122717 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.4884. Min Act: -0.1700
Data Index: 4358643 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0509. Min Range: -7.0509
Max Act: 6.4884. Min Act: -0.1700
Data Index: 7412195 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19