Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5898. Min Range: -7.5898
Max Act: 7.5898. Min Act: -0.1700
Data Index: 910250 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5898. Min Range: -7.5898
Max Act: 7.1836. Min Act: -0.1700
Data Index: 3823722 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5898. Min Range: -7.5898
Max Act: 7.1211. Min Act: -0.1700
Data Index: 4796715 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5898. Min Range: -7.5898
Max Act: 7.0586. Min Act: -0.1700
Data Index: 8720858 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5898. Min Range: -7.5898
Max Act: 7.0586. Min Act: -0.1700
Data Index: 7521209 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.9961. Min Act: -0.1700
Data Index: 5892953 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.9023. Min Act: -0.1700
Data Index: 7197179 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.9023. Min Act: -0.1700
Data Index: 4806357 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.8398. Min Act: -0.1700
Data Index: 4542909 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.8711. Min Act: -0.1700
Data Index: 7496629 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.8398. Min Act: -0.1700
Data Index: 400730 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.8086. Min Act: -0.1700
Data Index: 5621567 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.8086. Min Act: -0.1700
Data Index: 5686109 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.7773. Min Act: -0.1700
Data Index: 2110279 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.7461. Min Act: -0.1700
Data Index: 1660109 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.7148. Min Act: -0.1700
Data Index: 2963844 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.7461. Min Act: -0.1700
Data Index: 2817068 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.7148. Min Act: -0.1700
Data Index: 7157473 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.7148. Min Act: -0.1700
Data Index: 958189 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5898. Min Range: -7.5898
Max Act: 6.6836. Min Act: -0.1700
Data Index: 4037605 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19