Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5142 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4353. Min Range: -4.4353
Max Act: 4.4353. Min Act: -0.1700
Data Index: 4589989 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.9977. Min Act: -0.1700
Data Index: 533875 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.9977. Min Act: -0.1700
Data Index: 5206480 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.9665. Min Act: -0.1700
Data Index: 3294790 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.9040. Min Act: -0.1700
Data Index: 7630316 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8727. Min Act: -0.1700
Data Index: 3827884 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8727. Min Act: -0.1700
Data Index: 2090835 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8727. Min Act: -0.1700
Data Index: 1855062 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8727. Min Act: -0.1700
Data Index: 1287301 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8727. Min Act: -0.1700
Data Index: 3646218 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8571. Min Act: -0.1700
Data Index: 6840985 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8414. Min Act: -0.1700
Data Index: 3253470 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8258. Min Act: -0.1700
Data Index: 2552998 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8258. Min Act: -0.1700
Data Index: 2632504 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8414. Min Act: -0.1700
Data Index: 2250855 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8101. Min Act: -0.1700
Data Index: 2154994 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8258. Min Act: -0.1700
Data Index: 8734809 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8101. Min Act: -0.1700
Data Index: 3488869 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.8101. Min Act: -0.1700
Data Index: 4298374 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4353. Min Range: -4.4353
Max Act: 3.7945. Min Act: -0.1700
Data Index: 2469233 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19