Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3212. Min Range: -12.3212
Max Act: 12.3212. Min Act: -0.1700
Data Index: 5364867 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3212. Min Range: -12.3212
Max Act: 12.1962. Min Act: -0.1700
Data Index: 314453 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3212. Min Range: -12.3212
Max Act: 12.0712. Min Act: -0.1700
Data Index: 6447709 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3212. Min Range: -12.3212
Max Act: 12.0087. Min Act: -0.1700
Data Index: 2861337 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.8837. Min Act: -0.1700
Data Index: 467401 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.9462. Min Act: -0.1700
Data Index: 4166973 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.8837. Min Act: -0.1700
Data Index: 6441108 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.8837. Min Act: -0.1700
Data Index: 405195 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.8837. Min Act: -0.1700
Data Index: 8636617 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.8212. Min Act: -0.1700
Data Index: 849556 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.8212. Min Act: -0.1700
Data Index: 319179 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.8212. Min Act: -0.1700
Data Index: 651609 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.8212. Min Act: -0.1700
Data Index: 5156087 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.7587. Min Act: -0.1700
Data Index: 8612797 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.8212. Min Act: -0.1700
Data Index: 5328721 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.7587. Min Act: -0.1700
Data Index: 6504963 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.8212. Min Act: -0.1700
Data Index: 4345838 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.7587. Min Act: -0.1700
Data Index: 5392021 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.7587. Min Act: -0.1700
Data Index: 1683145 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3212. Min Range: -12.3212
Max Act: 11.7587. Min Act: -0.1700
Data Index: 5991358 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19