Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1554 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.8968. Min Act: -0.1700
Data Index: 7827493 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.7405. Min Act: -0.1700
Data Index: 1182500 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.6468. Min Act: -0.1700
Data Index: 2842906 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.5218. Min Act: -0.1700
Data Index: 2415587 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.4905. Min Act: -0.1700
Data Index: 4650480 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.3030. Min Act: -0.1700
Data Index: 2765767 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.3343. Min Act: -0.1700
Data Index: 6586607 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.3655. Min Act: -0.1700
Data Index: 4913003 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.3030. Min Act: -0.1700
Data Index: 5991529 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.2093. Min Act: -0.1700
Data Index: 702141 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.2718. Min Act: -0.1700
Data Index: 820967 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.2093. Min Act: -0.1700
Data Index: 5325998 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.1780. Min Act: -0.1700
Data Index: 2600094 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.2093. Min Act: -0.1700
Data Index: 61086 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.2093. Min Act: -0.1700
Data Index: 5051972 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.2093. Min Act: -0.1700
Data Index: 946624 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.1468. Min Act: -0.1700
Data Index: 321982 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.1155. Min Act: -0.1700
Data Index: 4534809 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.1780. Min Act: -0.1700
Data Index: 7724204 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8968. Min Range: -6.8968
Max Act: 6.0843. Min Act: -0.1700
Data Index: 5686420 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19