Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.6015. Min Act: -0.1700
Data Index: 6318776 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.5077. Min Act: -0.1700
Data Index: 458504 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.3827. Min Act: -0.1700
Data Index: 2255773 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.3202. Min Act: -0.1700
Data Index: 6803643 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.2890. Min Act: -0.1700
Data Index: 8513986 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.1640. Min Act: -0.1700
Data Index: 6034490 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.1640. Min Act: -0.1700
Data Index: 6196944 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.1327. Min Act: -0.1700
Data Index: 6958520 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.1327. Min Act: -0.1700
Data Index: 3483098 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.0702. Min Act: -0.1700
Data Index: 6138595 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.0702. Min Act: -0.1700
Data Index: 6734646 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.0390. Min Act: -0.1700
Data Index: 2920642 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.0390. Min Act: -0.1700
Data Index: 4962798 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.0390. Min Act: -0.1700
Data Index: 2130799 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6015. Min Range: -5.6015
Max Act: 5.0390. Min Act: -0.1700
Data Index: 6353996 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6015. Min Range: -5.6015
Max Act: 4.9765. Min Act: -0.1700
Data Index: 877375 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6015. Min Range: -5.6015
Max Act: 4.9452. Min Act: -0.1700
Data Index: 7013618 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6015. Min Range: -5.6015
Max Act: 4.9452. Min Act: -0.1700
Data Index: 8195904 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6015. Min Range: -5.6015
Max Act: 4.9452. Min Act: -0.1700
Data Index: 4082649 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6015. Min Range: -5.6015
Max Act: 4.9140. Min Act: -0.1700
Data Index: 7976856 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19