Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 529 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1735. Min Range: -7.1735
Max Act: 7.1735. Min Act: -0.1700
Data Index: 3868941 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.8610. Min Act: -0.1700
Data Index: 6784095 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.8298. Min Act: -0.1700
Data Index: 216372 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7985. Min Act: -0.1700
Data Index: 6178454 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7673. Min Act: -0.1700
Data Index: 7908053 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.7360. Min Act: -0.1700
Data Index: 4465890 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.6423. Min Act: -0.1700
Data Index: 448992 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.6735. Min Act: -0.1700
Data Index: 7143321 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.6110. Min Act: -0.1700
Data Index: 4913321 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.6110. Min Act: -0.1700
Data Index: 4913320 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.5798. Min Act: -0.1700
Data Index: 3257078 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.5798. Min Act: -0.1700
Data Index: 1268958 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.5798. Min Act: -0.1700
Data Index: 5712009 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.5798. Min Act: -0.1700
Data Index: 5085779 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.6110. Min Act: -0.1700
Data Index: 5149731 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.6423. Min Act: -0.1700
Data Index: 225985 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.6423. Min Act: -0.1700
Data Index: 835135 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.5798. Min Act: -0.1700
Data Index: 5817024 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.5485. Min Act: -0.1700
Data Index: 1593553 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1735. Min Range: -7.1735
Max Act: 6.5798. Min Act: -0.1700
Data Index: 4243926 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19