Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4782 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.9981. Min Act: -0.1700
Data Index: 2327378 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.8731. Min Act: -0.1700
Data Index: 6591262 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.6856. Min Act: -0.1700
Data Index: 3324350 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.5606. Min Act: -0.1700
Data Index: 342923 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.5606. Min Act: -0.1700
Data Index: 2493524 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.4981. Min Act: -0.1700
Data Index: 5707783 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.4356. Min Act: -0.1700
Data Index: 7585647 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.4356. Min Act: -0.1700
Data Index: 2635735 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.4356. Min Act: -0.1700
Data Index: 3845329 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.3731. Min Act: -0.1700
Data Index: 1704820 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.3106. Min Act: -0.1700
Data Index: 2165105 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.2481. Min Act: -0.1700
Data Index: 2182785 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.3106. Min Act: -0.1700
Data Index: 3302047 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.2481. Min Act: -0.1700
Data Index: 5567378 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.1856. Min Act: -0.1700
Data Index: 7425830 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.1856. Min Act: -0.1700
Data Index: 5078815 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.1231. Min Act: -0.1700
Data Index: 2165315 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.1231. Min Act: -0.1700
Data Index: 5100494 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.1231. Min Act: -0.1700
Data Index: 1479818 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9981. Min Range: -10.9981
Max Act: 10.1231. Min Act: -0.1700
Data Index: 4082550 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19