Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3663 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3000. Min Range: -7.3000
Max Act: 7.3000. Min Act: -0.1700
Data Index: 2398929 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3000. Min Range: -7.3000
Max Act: 7.2062. Min Act: -0.1700
Data Index: 2683050 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3000. Min Range: -7.3000
Max Act: 7.1125. Min Act: -0.1700
Data Index: 1883129 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3000. Min Range: -7.3000
Max Act: 7.0187. Min Act: -0.1700
Data Index: 7521834 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.9562. Min Act: -0.1700
Data Index: 2103419 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.8937. Min Act: -0.1700
Data Index: 8201773 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.8312. Min Act: -0.1700
Data Index: 4401713 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.7687. Min Act: -0.1700
Data Index: 3920551 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.7687. Min Act: -0.1700
Data Index: 2059516 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.7687. Min Act: -0.1700
Data Index: 7088317 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.7375. Min Act: -0.1700
Data Index: 7721391 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.7375. Min Act: -0.1700
Data Index: 3843141 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.6750. Min Act: -0.1700
Data Index: 5387297 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.6750. Min Act: -0.1700
Data Index: 1410095 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.6125. Min Act: -0.1700
Data Index: 5635496 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.5812. Min Act: -0.1700
Data Index: 1249677 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.5500. Min Act: -0.1700
Data Index: 236150 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.5500. Min Act: -0.1700
Data Index: 7901841 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.5187. Min Act: -0.1700
Data Index: 5417220 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3000. Min Range: -7.3000
Max Act: 6.5500. Min Act: -0.1700
Data Index: 6427229 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19