Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4134. Min Range: -10.4134
Max Act: 10.4134. Min Act: -0.1700
Data Index: 6880303 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4134. Min Range: -10.4134
Max Act: 10.2259. Min Act: -0.1700
Data Index: 3501991 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4134. Min Range: -10.4134
Max Act: 10.2259. Min Act: -0.1700
Data Index: 1245911 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4134. Min Range: -10.4134
Max Act: 10.1009. Min Act: -0.1700
Data Index: 3161426 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4134. Min Range: -10.4134
Max Act: 10.0384. Min Act: -0.1700
Data Index: 3959558 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4134. Min Range: -10.4134
Max Act: 10.1009. Min Act: -0.1700
Data Index: 7677171 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.9759. Min Act: -0.1700
Data Index: 4609864 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.9134. Min Act: -0.1700
Data Index: 4351682 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.9134. Min Act: -0.1700
Data Index: 5747757 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.9759. Min Act: -0.1700
Data Index: 8391356 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.9134. Min Act: -0.1700
Data Index: 1798917 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.8509. Min Act: -0.1700
Data Index: 3317415 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.9134. Min Act: -0.1700
Data Index: 49538 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.9134. Min Act: -0.1700
Data Index: 7086275 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.8509. Min Act: -0.1700
Data Index: 8454298 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.7884. Min Act: -0.1700
Data Index: 354798 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.7884. Min Act: -0.1700
Data Index: 5614863 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.7884. Min Act: -0.1700
Data Index: 6612612 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.7259. Min Act: -0.1700
Data Index: 3449682 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4134. Min Range: -10.4134
Max Act: 9.7259. Min Act: -0.1700
Data Index: 4754420 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19