Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 771 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0250. Min Range: -7.0250
Max Act: 7.0250. Min Act: -0.1700
Data Index: 6811037 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.9000. Min Act: -0.1700
Data Index: 780330 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.6500. Min Act: -0.1700
Data Index: 339641 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.6188. Min Act: -0.1700
Data Index: 1937027 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.5875. Min Act: -0.1700
Data Index: 5267366 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.5875. Min Act: -0.1700
Data Index: 292571 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.4938. Min Act: -0.1700
Data Index: 7655847 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.5250. Min Act: -0.1700
Data Index: 8068793 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.4938. Min Act: -0.1700
Data Index: 7957912 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.4625. Min Act: -0.1700
Data Index: 8430450 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.4000. Min Act: -0.1700
Data Index: 4175045 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.4000. Min Act: -0.1700
Data Index: 1614143 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.3063. Min Act: -0.1700
Data Index: 6064704 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.3063. Min Act: -0.1700
Data Index: 2004830 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.3063. Min Act: -0.1700
Data Index: 3459213 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.3375. Min Act: -0.1700
Data Index: 3104846 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.3375. Min Act: -0.1700
Data Index: 4261983 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.3375. Min Act: -0.1700
Data Index: 2754688 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.2438. Min Act: -0.1700
Data Index: 1535693 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0250. Min Range: -7.0250
Max Act: 6.2438. Min Act: -0.1700
Data Index: 7401723 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19