Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.2079. Min Act: -0.1700
Data Index: 4020607 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.1767. Min Act: -0.1700
Data Index: 5101256 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.1767. Min Act: -0.1700
Data Index: 7816291 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.1454. Min Act: -0.1700
Data Index: 912564 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.1141. Min Act: -0.1700
Data Index: 5162503 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0829. Min Act: -0.1700
Data Index: 4469298 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0829. Min Act: -0.1700
Data Index: 4546424 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0516. Min Act: -0.1700
Data Index: 5774490 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0829. Min Act: -0.1700
Data Index: 1847158 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.1141. Min Act: -0.1700
Data Index: 8807808 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0204. Min Act: -0.1700
Data Index: 1990427 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0516. Min Act: -0.1700
Data Index: 2934371 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0829. Min Act: -0.1700
Data Index: 889806 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0516. Min Act: -0.1700
Data Index: 1795255 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0516. Min Act: -0.1700
Data Index: 8092235 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0204. Min Act: -0.1700
Data Index: 6019820 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0516. Min Act: -0.1700
Data Index: 87733 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0204. Min Act: -0.1700
Data Index: 830954 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2079. Min Range: -4.2079
Max Act: 3.9891. Min Act: -0.1700
Data Index: 5189101 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2079. Min Range: -4.2079
Max Act: 4.0204. Min Act: -0.1700
Data Index: 4203896 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19