Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.5850. Min Act: -0.1700
Data Index: 8554477 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.3975. Min Act: -0.1700
Data Index: 498163 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.2725. Min Act: -0.1700
Data Index: 3372284 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.2725. Min Act: -0.1700
Data Index: 5223256 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.2412. Min Act: -0.1700
Data Index: 5658439 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.2100. Min Act: -0.1700
Data Index: 5258242 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.1475. Min Act: -0.1700
Data Index: 2167034 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.0537. Min Act: -0.1700
Data Index: 5346139 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.0850. Min Act: -0.1700
Data Index: 8634306 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.0537. Min Act: -0.1700
Data Index: 7047992 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5850. Min Range: -7.5850
Max Act: 7.0225. Min Act: -0.1700
Data Index: 1398559 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5850. Min Range: -7.5850
Max Act: 6.9600. Min Act: -0.1700
Data Index: 736706 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5850. Min Range: -7.5850
Max Act: 6.9912. Min Act: -0.1700
Data Index: 6148898 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5850. Min Range: -7.5850
Max Act: 6.9287. Min Act: -0.1700
Data Index: 7858005 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5850. Min Range: -7.5850
Max Act: 6.9287. Min Act: -0.1700
Data Index: 6834754 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5850. Min Range: -7.5850
Max Act: 6.9287. Min Act: -0.1700
Data Index: 681861 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5850. Min Range: -7.5850
Max Act: 6.9600. Min Act: -0.1700
Data Index: 4438933 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5850. Min Range: -7.5850
Max Act: 6.9287. Min Act: -0.1700
Data Index: 6543081 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5850. Min Range: -7.5850
Max Act: 6.8662. Min Act: -0.1700
Data Index: 7716571 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5850. Min Range: -7.5850
Max Act: 6.8662. Min Act: -0.1700
Data Index: 8301108 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19