Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4674. Min Range: -8.4674
Max Act: 8.4674. Min Act: -0.1700
Data Index: 2279682 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.9674. Min Act: -0.1700
Data Index: 7840793 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.8424. Min Act: -0.1700
Data Index: 8577945 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.8424. Min Act: -0.1700
Data Index: 658916 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.7174. Min Act: -0.1700
Data Index: 414267 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.6861. Min Act: -0.1700
Data Index: 6571013 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.6861. Min Act: -0.1700
Data Index: 3631219 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.6549. Min Act: -0.1700
Data Index: 7976774 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.6549. Min Act: -0.1700
Data Index: 987481 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.6549. Min Act: -0.1700
Data Index: 3688805 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.6549. Min Act: -0.1700
Data Index: 7048510 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.6236. Min Act: -0.1700
Data Index: 7360565 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.6236. Min Act: -0.1700
Data Index: 654194 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.6236. Min Act: -0.1700
Data Index: 4675391 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.5924. Min Act: -0.1700
Data Index: 5108898 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.5924. Min Act: -0.1700
Data Index: 1674667 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.5611. Min Act: -0.1700
Data Index: 1064650 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.5611. Min Act: -0.1700
Data Index: 2585138 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.5611. Min Act: -0.1700
Data Index: 3698751 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4674. Min Range: -8.4674
Max Act: 7.5299. Min Act: -0.1700
Data Index: 71480 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19