Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2783 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.9775. Min Act: -0.1700
Data Index: 4717835 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.8837. Min Act: -0.1700
Data Index: 7239582 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.6025. Min Act: -0.1700
Data Index: 1557382 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.5400. Min Act: -0.1700
Data Index: 8075249 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.5087. Min Act: -0.1700
Data Index: 2743425 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.5087. Min Act: -0.1700
Data Index: 744557 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.4462. Min Act: -0.1700
Data Index: 484492 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.4150. Min Act: -0.1700
Data Index: 1710575 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.4150. Min Act: -0.1700
Data Index: 2584566 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.4150. Min Act: -0.1700
Data Index: 649827 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.3837. Min Act: -0.1700
Data Index: 6086605 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.3525. Min Act: -0.1700
Data Index: 1777853 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.3525. Min Act: -0.1700
Data Index: 2405558 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.3525. Min Act: -0.1700
Data Index: 8298279 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.3212. Min Act: -0.1700
Data Index: 6891880 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.3212. Min Act: -0.1700
Data Index: 2478416 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.3212. Min Act: -0.1700
Data Index: 883085 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.3212. Min Act: -0.1700
Data Index: 3139639 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.2587. Min Act: -0.1700
Data Index: 3053722 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9775. Min Range: -4.9775
Max Act: 4.2900. Min Act: -0.1700
Data Index: 4066700 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19