Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4079 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.4075. Min Act: -0.1700
Data Index: 5996613 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.3748. Min Act: -0.1700
Data Index: 6792336 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.3584. Min Act: -0.1700
Data Index: 1593796 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2598. Min Act: -0.1700
Data Index: 7984555 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2267. Min Act: -0.1700
Data Index: 5452358 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2267. Min Act: -0.1700
Data Index: 2126034 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2102. Min Act: -0.1700
Data Index: 5754336 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2102. Min Act: -0.1700
Data Index: 7766212 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2267. Min Act: -0.1700
Data Index: 4232380 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2433. Min Act: -0.1700
Data Index: 7712865 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2102. Min Act: -0.1700
Data Index: 6463889 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2267. Min Act: -0.1700
Data Index: 1262490 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2267. Min Act: -0.1700
Data Index: 4814945 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2102. Min Act: -0.1700
Data Index: 2832392 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.1936. Min Act: -0.1700
Data Index: 5569140 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2102. Min Act: -0.1700
Data Index: 293569 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.1936. Min Act: -0.1700
Data Index: 146412 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.1936. Min Act: -0.1700
Data Index: 6956820 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.1936. Min Act: -0.1700
Data Index: 3564949 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4075. Min Range: -2.4075
Max Act: 2.2102. Min Act: -0.1700
Data Index: 396150 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19