Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9963. Min Act: -0.1700
Data Index: 6206029 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9709. Min Act: -0.1700
Data Index: 2385201 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9794. Min Act: -0.1700
Data Index: 4386510 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9709. Min Act: -0.1700
Data Index: 3383037 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9455. Min Act: -0.1700
Data Index: 2773177 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9540. Min Act: -0.1700
Data Index: 1857781 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9285. Min Act: -0.1700
Data Index: 7043180 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9285. Min Act: -0.1700
Data Index: 4114383 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9200. Min Act: -0.1700
Data Index: 5371522 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9285. Min Act: -0.1700
Data Index: 6211800 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9200. Min Act: -0.1700
Data Index: 6335927 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9115. Min Act: -0.1700
Data Index: 6214386 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.8944. Min Act: -0.1700
Data Index: 2257532 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.9029. Min Act: -0.1700
Data Index: 8271405 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.8944. Min Act: -0.1700
Data Index: 565451 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.8944. Min Act: -0.1700
Data Index: 521390 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.8944. Min Act: -0.1700
Data Index: 5487954 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.8859. Min Act: -0.1700
Data Index: 4659051 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.8773. Min Act: -0.1700
Data Index: 3722179 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9963. Min Range: -1.9963
Max Act: 1.8773. Min Act: -0.1700
Data Index: 3960410 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19