Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4397 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1393. Min Range: -7.1393
Max Act: 7.1393. Min Act: -0.1700
Data Index: 4785245 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1393. Min Range: -7.1393
Max Act: 7.0455. Min Act: -0.1700
Data Index: 3816156 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.9830. Min Act: -0.1700
Data Index: 2242090 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.8580. Min Act: -0.1700
Data Index: 1380337 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.8580. Min Act: -0.1700
Data Index: 5929391 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.7955. Min Act: -0.1700
Data Index: 6225521 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.7643. Min Act: -0.1700
Data Index: 6809503 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.7330. Min Act: -0.1700
Data Index: 4450770 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.7643. Min Act: -0.1700
Data Index: 6274424 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.7330. Min Act: -0.1700
Data Index: 1495718 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.7018. Min Act: -0.1700
Data Index: 8328356 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.6705. Min Act: -0.1700
Data Index: 1527739 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.6705. Min Act: -0.1700
Data Index: 1743227 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.6705. Min Act: -0.1700
Data Index: 7791589 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.7018. Min Act: -0.1700
Data Index: 7153107 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.6393. Min Act: -0.1700
Data Index: 7760717 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.6080. Min Act: -0.1700
Data Index: 7580656 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.6080. Min Act: -0.1700
Data Index: 6881119 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.5768. Min Act: -0.1700
Data Index: 5701864 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1393. Min Range: -7.1393
Max Act: 6.6080. Min Act: -0.1700
Data Index: 3406762 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19