Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2828 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.2905. Min Act: -0.1700
Data Index: 3973571 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.2280. Min Act: -0.1700
Data Index: 2035397 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.1967. Min Act: -0.1700
Data Index: 5707567 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.1655. Min Act: -0.1700
Data Index: 474299 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.1342. Min Act: -0.1700
Data Index: 8473073 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.1342. Min Act: -0.1700
Data Index: 6365669 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.0717. Min Act: -0.1700
Data Index: 7460905 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.1030. Min Act: -0.1700
Data Index: 6932268 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.0405. Min Act: -0.1700
Data Index: 4074366 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.0092. Min Act: -0.1700
Data Index: 3870157 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.0092. Min Act: -0.1700
Data Index: 7645708 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2905. Min Range: -6.2905
Max Act: 5.9780. Min Act: -0.1700
Data Index: 2236609 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2905. Min Range: -6.2905
Max Act: 5.9780. Min Act: -0.1700
Data Index: 3391775 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2905. Min Range: -6.2905
Max Act: 6.0092. Min Act: -0.1700
Data Index: 5474573 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2905. Min Range: -6.2905
Max Act: 5.9467. Min Act: -0.1700
Data Index: 7548642 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2905. Min Range: -6.2905
Max Act: 5.9467. Min Act: -0.1700
Data Index: 1094846 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2905. Min Range: -6.2905
Max Act: 5.9155. Min Act: -0.1700
Data Index: 557662 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2905. Min Range: -6.2905
Max Act: 5.9467. Min Act: -0.1700
Data Index: 3255325 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2905. Min Range: -6.2905
Max Act: 5.9155. Min Act: -0.1700
Data Index: 2467311 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2905. Min Range: -6.2905
Max Act: 5.9155. Min Act: -0.1700
Data Index: 4893739 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19