Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2227 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3034. Min Range: -7.3034
Max Act: 7.3034. Min Act: -0.1700
Data Index: 5373849 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.7721. Min Act: -0.1700
Data Index: 5781742 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.6784. Min Act: -0.1700
Data Index: 6020395 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.6471. Min Act: -0.1700
Data Index: 1398563 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.5221. Min Act: -0.1700
Data Index: 7346041 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.4909. Min Act: -0.1700
Data Index: 2223190 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.4909. Min Act: -0.1700
Data Index: 7398357 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.4909. Min Act: -0.1700
Data Index: 1857691 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.4596. Min Act: -0.1700
Data Index: 4180206 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.4596. Min Act: -0.1700
Data Index: 3304801 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.3971. Min Act: -0.1700
Data Index: 1358606 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.3659. Min Act: -0.1700
Data Index: 4298985 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.3971. Min Act: -0.1700
Data Index: 8233709 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.3659. Min Act: -0.1700
Data Index: 8290025 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.3659. Min Act: -0.1700
Data Index: 7717844 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.3659. Min Act: -0.1700
Data Index: 2261959 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.3659. Min Act: -0.1700
Data Index: 1333341 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.3346. Min Act: -0.1700
Data Index: 2476458 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.3034. Min Act: -0.1700
Data Index: 4722871 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3034. Min Range: -7.3034
Max Act: 6.3034. Min Act: -0.1700
Data Index: 2056742 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19