Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1782 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2742. Min Range: -8.2742
Max Act: 8.2742. Min Act: -0.1700
Data Index: 5958728 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2742. Min Range: -8.2742
Max Act: 8.0867. Min Act: -0.1700
Data Index: 1358998 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.9617. Min Act: -0.1700
Data Index: 5021180 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.9617. Min Act: -0.1700
Data Index: 4866041 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.8992. Min Act: -0.1700
Data Index: 2392688 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.8367. Min Act: -0.1700
Data Index: 1069009 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.8367. Min Act: -0.1700
Data Index: 6041951 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.8367. Min Act: -0.1700
Data Index: 3638774 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.8367. Min Act: -0.1700
Data Index: 7007604 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.8367. Min Act: -0.1700
Data Index: 5018091 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.8367. Min Act: -0.1700
Data Index: 6831728 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.8367. Min Act: -0.1700
Data Index: 4237064 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.8367. Min Act: -0.1700
Data Index: 1981216 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.8367. Min Act: -0.1700
Data Index: 3770231 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.7742. Min Act: -0.1700
Data Index: 4063193 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.7742. Min Act: -0.1700
Data Index: 1421100 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.7742. Min Act: -0.1700
Data Index: 5674138 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.7117. Min Act: -0.1700
Data Index: 866315 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.7117. Min Act: -0.1700
Data Index: 3190243 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2742. Min Range: -8.2742
Max Act: 7.7117. Min Act: -0.1700
Data Index: 4405913 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19