Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3875 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.2184. Min Act: -0.1700
Data Index: 431899 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.2184. Min Act: -0.1700
Data Index: 8735390 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.1871. Min Act: -0.1700
Data Index: 8735388 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.1558. Min Act: -0.1700
Data Index: 8761502 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.0933. Min Act: -0.1700
Data Index: 4061405 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.1246. Min Act: -0.1700
Data Index: 1969793 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.1246. Min Act: -0.1700
Data Index: 8043154 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.1246. Min Act: -0.1700
Data Index: 1276908 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.0933. Min Act: -0.1700
Data Index: 5107901 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.1246. Min Act: -0.1700
Data Index: 5751368 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.0933. Min Act: -0.1700
Data Index: 991594 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.1246. Min Act: -0.1700
Data Index: 6399934 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.0933. Min Act: -0.1700
Data Index: 8435103 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.0933. Min Act: -0.1700
Data Index: 975109 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.0621. Min Act: -0.1700
Data Index: 4287758 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.0621. Min Act: -0.1700
Data Index: 8735383 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.0933. Min Act: -0.1700
Data Index: 8530623 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.0308. Min Act: -0.1700
Data Index: 103739 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2184. Min Range: -4.2184
Max Act: 3.9996. Min Act: -0.1700
Data Index: 458600 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2184. Min Range: -4.2184
Max Act: 4.0308. Min Act: -0.1700
Data Index: 4061408 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19