Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.6996. Min Act: -0.1700
Data Index: 3060305 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.6562. Min Act: -0.1682
Data Index: 4824400 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.6126. Min Act: -0.1700
Data Index: 3334215 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.6039. Min Act: -0.1699
Data Index: 609095 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5951. Min Act: -0.1700
Data Index: 5885978 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5864. Min Act: -0.1700
Data Index: 4321542 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5951. Min Act: -0.1696
Data Index: 3734339 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5777. Min Act: -0.1698
Data Index: 4548757 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5602. Min Act: -0.1700
Data Index: 1174994 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5514. Min Act: -0.1700
Data Index: 5531577 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5514. Min Act: -0.1700
Data Index: 8692462 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5427. Min Act: -0.1699
Data Index: 956714 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5427. Min Act: -0.1700
Data Index: 8679468 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5427. Min Act: -0.1699
Data Index: 2377196 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5427. Min Act: -0.1700
Data Index: 1052145 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5339. Min Act: -0.1699
Data Index: 4426135 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5339. Min Act: -0.1700
Data Index: 6427401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5251. Min Act: -0.1699
Data Index: 2216430 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5427. Min Act: -0.1699
Data Index: 2666633 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6996. Min Range: -1.6996
Max Act: 1.5251. Min Act: -0.1697
Data Index: 2319773 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19