Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3124 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.8986. Min Act: -0.1700
Data Index: 5129734 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.6798. Min Act: -0.1700
Data Index: 8111492 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.6173. Min Act: -0.1700
Data Index: 414002 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.5236. Min Act: -0.1700
Data Index: 5040769 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.4923. Min Act: -0.1700
Data Index: 7345243 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.4611. Min Act: -0.1700
Data Index: 3635441 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.4611. Min Act: -0.1700
Data Index: 3989902 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.4298. Min Act: -0.1700
Data Index: 7913785 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.4298. Min Act: -0.1700
Data Index: 136236 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.4298. Min Act: -0.1700
Data Index: 8684199 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.4298. Min Act: -0.1700
Data Index: 2691571 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.3986. Min Act: -0.1700
Data Index: 2326932 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.3986. Min Act: -0.1700
Data Index: 4980053 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.3673. Min Act: -0.1700
Data Index: 7331247 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.3673. Min Act: -0.1700
Data Index: 1500206 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.3673. Min Act: -0.1700
Data Index: 5615535 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.3361. Min Act: -0.1700
Data Index: 7249874 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.3361. Min Act: -0.1700
Data Index: 6551133 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.3048. Min Act: -0.1700
Data Index: 4810008 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8986. Min Range: -4.8986
Max Act: 4.3048. Min Act: -0.1700
Data Index: 2557660 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19