Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 692 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.9922. Min Act: -0.1700
Data Index: 1027530 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.9922. Min Act: -0.1700
Data Index: 8680198 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.9609. Min Act: -0.1700
Data Index: 7922445 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.8984. Min Act: -0.1700
Data Index: 2538825 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.8359. Min Act: -0.1700
Data Index: 2393625 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.8359. Min Act: -0.1700
Data Index: 2304589 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.8672. Min Act: -0.1700
Data Index: 6855870 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.8047. Min Act: -0.1700
Data Index: 4080354 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7734. Min Act: -0.1700
Data Index: 8384278 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7734. Min Act: -0.1700
Data Index: 5591888 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7734. Min Act: -0.1700
Data Index: 1386192 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7422. Min Act: -0.1700
Data Index: 7025848 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7422. Min Act: -0.1700
Data Index: 6597030 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7109. Min Act: -0.1700
Data Index: 3278052 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7109. Min Act: -0.1700
Data Index: 6988045 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.6797. Min Act: -0.1700
Data Index: 7033876 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7109. Min Act: -0.1700
Data Index: 5056656 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7422. Min Act: -0.1700
Data Index: 4277730 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7109. Min Act: -0.1700
Data Index: 5580969 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9922. Min Range: -4.9922
Max Act: 4.7109. Min Act: -0.1700
Data Index: 5630571 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19