Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0182. Min Range: -8.0182
Max Act: 8.0182. Min Act: -0.1700
Data Index: 3643760 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.6120. Min Act: -0.1700
Data Index: 2264613 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.5807. Min Act: -0.1700
Data Index: 8174944 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.4870. Min Act: -0.1700
Data Index: 6151888 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.4245. Min Act: -0.1700
Data Index: 1329863 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.3932. Min Act: -0.1700
Data Index: 8345969 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.3932. Min Act: -0.1700
Data Index: 2074841 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.3932. Min Act: -0.1700
Data Index: 8789755 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.2995. Min Act: -0.1700
Data Index: 6187987 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.2995. Min Act: -0.1700
Data Index: 500979 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.2057. Min Act: -0.1700
Data Index: 1751565 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.2057. Min Act: -0.1700
Data Index: 5716837 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.1745. Min Act: -0.1700
Data Index: 6915501 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.1745. Min Act: -0.1700
Data Index: 1032293 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.1745. Min Act: -0.1700
Data Index: 5001827 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.1745. Min Act: -0.1700
Data Index: 4396089 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.1120. Min Act: -0.1700
Data Index: 7818478 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.1120. Min Act: -0.1700
Data Index: 3228882 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.1432. Min Act: -0.1700
Data Index: 977881 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0182. Min Range: -8.0182
Max Act: 7.0807. Min Act: -0.1700
Data Index: 875040 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19