Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3890 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.9044. Min Act: -0.1700
Data Index: 6318751 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.8731. Min Act: -0.1700
Data Index: 8787097 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.8419. Min Act: -0.1700
Data Index: 264036 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.8106. Min Act: -0.1700
Data Index: 4460571 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.6231. Min Act: -0.1700
Data Index: 5866723 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5606. Min Act: -0.1700
Data Index: 1596424 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5919. Min Act: -0.1700
Data Index: 2349276 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5919. Min Act: -0.1700
Data Index: 6847818 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5606. Min Act: -0.1700
Data Index: 2406000 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5606. Min Act: -0.1700
Data Index: 7092723 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5606. Min Act: -0.1700
Data Index: 7041975 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5294. Min Act: -0.1700
Data Index: 1607066 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4981. Min Act: -0.1700
Data Index: 4959919 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5294. Min Act: -0.1700
Data Index: 586716 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5294. Min Act: -0.1700
Data Index: 104034 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5294. Min Act: -0.1700
Data Index: 5480901 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4669. Min Act: -0.1700
Data Index: 4392763 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4981. Min Act: -0.1700
Data Index: 2167766 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.4981. Min Act: -0.1700
Data Index: 1573828 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9044. Min Range: -4.9044
Max Act: 4.5294. Min Act: -0.1700
Data Index: 6532232 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19