Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2792 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0120. Min Range: -9.0120
Max Act: 9.0120. Min Act: -0.1700
Data Index: 5175675 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.9495. Min Act: -0.1700
Data Index: 6162309 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.8245. Min Act: -0.1700
Data Index: 4770088 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.7620. Min Act: -0.1700
Data Index: 6389551 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.6995. Min Act: -0.1700
Data Index: 6389550 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.6370. Min Act: -0.1700
Data Index: 6894489 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.5745. Min Act: -0.1700
Data Index: 1867546 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.5745. Min Act: -0.1700
Data Index: 2834328 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.5120. Min Act: -0.1700
Data Index: 4880529 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.5120. Min Act: -0.1700
Data Index: 3481345 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.5120. Min Act: -0.1700
Data Index: 3569752 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.4808. Min Act: -0.1700
Data Index: 4520985 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.4808. Min Act: -0.1700
Data Index: 4948775 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.4808. Min Act: -0.1700
Data Index: 2413530 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.4495. Min Act: -0.1700
Data Index: 4618936 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.3870. Min Act: -0.1700
Data Index: 5892748 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.3870. Min Act: -0.1700
Data Index: 7489869 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.3558. Min Act: -0.1700
Data Index: 423436 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.3558. Min Act: -0.1700
Data Index: 4770087 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0120. Min Range: -9.0120
Max Act: 8.3558. Min Act: -0.1700
Data Index: 8043011 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19