Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4452 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.7051. Min Act: -0.1700
Data Index: 8659113 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.6426. Min Act: -0.1700
Data Index: 237980 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.6426. Min Act: -0.1700
Data Index: 4603668 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.6426. Min Act: -0.1700
Data Index: 1375113 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.4551. Min Act: -0.1700
Data Index: 8198901 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.5176. Min Act: -0.1700
Data Index: 481834 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.4551. Min Act: -0.1700
Data Index: 4618297 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.4551. Min Act: -0.1700
Data Index: 255175 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.4551. Min Act: -0.1700
Data Index: 5104382 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.4551. Min Act: -0.1700
Data Index: 4174475 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.4551. Min Act: -0.1700
Data Index: 4135403 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.4551. Min Act: -0.1700
Data Index: 8298585 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.5176. Min Act: -0.1700
Data Index: 4884162 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.4551. Min Act: -0.1700
Data Index: 3133512 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.3926. Min Act: -0.1700
Data Index: 381749 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.3926. Min Act: -0.1700
Data Index: 7283247 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.3926. Min Act: -0.1700
Data Index: 1465171 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.3301. Min Act: -0.1700
Data Index: 4590436 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.3301. Min Act: -0.1700
Data Index: 7479422 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.3301. Min Act: -0.1700
Data Index: 4046621 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19