Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.4625. Min Act: -0.1700
Data Index: 7292406 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.4625. Min Act: -0.1700
Data Index: 5362751 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.4313. Min Act: -0.1700
Data Index: 4792012 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.3063. Min Act: -0.1700
Data Index: 5994296 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.3063. Min Act: -0.1700
Data Index: 5996696 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.3375. Min Act: -0.1700
Data Index: 3384922 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.2750. Min Act: -0.1700
Data Index: 5876947 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.2125. Min Act: -0.1700
Data Index: 7230336 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.2125. Min Act: -0.1700
Data Index: 4063924 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.2125. Min Act: -0.1700
Data Index: 8221900 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.1188. Min Act: -0.1700
Data Index: 2396289 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.0875. Min Act: -0.1700
Data Index: 8015092 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.0563. Min Act: -0.1700
Data Index: 1726879 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.0563. Min Act: -0.1700
Data Index: 3327893 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4625. Min Range: -7.4625
Max Act: 6.9938. Min Act: -0.1700
Data Index: 2924387 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4625. Min Range: -7.4625
Max Act: 6.9938. Min Act: -0.1700
Data Index: 8480859 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4625. Min Range: -7.4625
Max Act: 7.0250. Min Act: -0.1700
Data Index: 2995835 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4625. Min Range: -7.4625
Max Act: 6.9938. Min Act: -0.1700
Data Index: 4911371 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4625. Min Range: -7.4625
Max Act: 6.9625. Min Act: -0.1700
Data Index: 4063925 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4625. Min Range: -7.4625
Max Act: 6.9938. Min Act: -0.1700
Data Index: 6362474 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19