Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.7768. Min Act: -0.1700
Data Index: 7245078 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.6830. Min Act: -0.1700
Data Index: 729908 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.5893. Min Act: -0.1700
Data Index: 2272001 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.5580. Min Act: -0.1700
Data Index: 6990471 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.5268. Min Act: -0.1700
Data Index: 7349144 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4955. Min Act: -0.1700
Data Index: 1022629 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4955. Min Act: -0.1700
Data Index: 6173660 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4643. Min Act: -0.1700
Data Index: 2052868 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4330. Min Act: -0.1700
Data Index: 3086959 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4018. Min Act: -0.1700
Data Index: 5783134 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4018. Min Act: -0.1700
Data Index: 7961453 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.3705. Min Act: -0.1700
Data Index: 181243 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4330. Min Act: -0.1700
Data Index: 2300709 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.4018. Min Act: -0.1700
Data Index: 7251368 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.3705. Min Act: -0.1700
Data Index: 161008 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.3080. Min Act: -0.1700
Data Index: 3693854 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.2768. Min Act: -0.1700
Data Index: 7984019 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.3393. Min Act: -0.1700
Data Index: 1978832 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.2768. Min Act: -0.1700
Data Index: 3724815 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7768. Min Range: -6.7768
Max Act: 6.2768. Min Act: -0.1700
Data Index: 5958394 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19