Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 820 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.7173. Min Act: -0.1700
Data Index: 4710320 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.5923. Min Act: -0.1700
Data Index: 4884480 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.4673. Min Act: -0.1699
Data Index: 2323263 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.4673. Min Act: -0.1700
Data Index: 2144970 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.4673. Min Act: -0.1700
Data Index: 565139 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.4048. Min Act: -0.1700
Data Index: 3796397 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.4048. Min Act: -0.1700
Data Index: 8428402 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.3736. Min Act: -0.1700
Data Index: 424683 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.2798. Min Act: -0.1700
Data Index: 1059116 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.3111. Min Act: -0.1700
Data Index: 2902195 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.2173. Min Act: -0.1700
Data Index: 5130080 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.2486. Min Act: -0.1700
Data Index: 2844359 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.2486. Min Act: -0.1700
Data Index: 7258080 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.2486. Min Act: -0.1700
Data Index: 4931324 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.2486. Min Act: -0.1700
Data Index: 5906656 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.1861. Min Act: -0.1700
Data Index: 1132632 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.2173. Min Act: -0.1700
Data Index: 892765 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.2486. Min Act: -0.1700
Data Index: 4018700 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.2173. Min Act: -0.1700
Data Index: 8047057 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7173. Min Range: -7.7173
Max Act: 7.1861. Min Act: -0.1700
Data Index: 5526327 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19