Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.5603. Min Act: -0.1700
Data Index: 5729941 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.4978. Min Act: -0.1700
Data Index: 4621139 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.5291. Min Act: -0.1700
Data Index: 90594 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.4666. Min Act: -0.1700
Data Index: 362227 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.4666. Min Act: -0.1700
Data Index: 802257 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.4353. Min Act: -0.1700
Data Index: 3444927 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.4353. Min Act: -0.1700
Data Index: 2541581 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.4353. Min Act: -0.1700
Data Index: 1061953 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.4353. Min Act: -0.1700
Data Index: 5196131 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.4041. Min Act: -0.1700
Data Index: 2599725 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.4041. Min Act: -0.1700
Data Index: 4502758 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.3416. Min Act: -0.1700
Data Index: 6738837 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.3416. Min Act: -0.1700
Data Index: 2877970 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.3416. Min Act: -0.1700
Data Index: 1507654 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.3416. Min Act: -0.1700
Data Index: 4453522 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.3103. Min Act: -0.1700
Data Index: 1529403 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.3103. Min Act: -0.1700
Data Index: 4427613 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.3103. Min Act: -0.1700
Data Index: 7345013 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.3103. Min Act: -0.1700
Data Index: 1090551 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5603. Min Range: -4.5603
Max Act: 4.3103. Min Act: -0.1700
Data Index: 3131462 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19