Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3759. Min Range: -6.3759
Max Act: 6.3759. Min Act: -0.1700
Data Index: 1747854 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3759. Min Range: -6.3759
Max Act: 6.0009. Min Act: -0.1700
Data Index: 4558522 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.7509. Min Act: -0.1700
Data Index: 4579578 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.7196. Min Act: -0.1700
Data Index: 6322191 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.6259. Min Act: -0.1700
Data Index: 7481233 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.6259. Min Act: -0.1700
Data Index: 6105549 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.5946. Min Act: -0.1700
Data Index: 3369123 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.5634. Min Act: -0.1700
Data Index: 7498265 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.5946. Min Act: -0.1700
Data Index: 6027216 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.5009. Min Act: -0.1700
Data Index: 6250719 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.5009. Min Act: -0.1700
Data Index: 5241058 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.4384. Min Act: -0.1700
Data Index: 6405350 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.4696. Min Act: -0.1700
Data Index: 5742817 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.4696. Min Act: -0.1700
Data Index: 5202063 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.4384. Min Act: -0.1700
Data Index: 8504529 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.4071. Min Act: -0.1700
Data Index: 6392280 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.4071. Min Act: -0.1700
Data Index: 5668807 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.3759. Min Act: -0.1700
Data Index: 4130400 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.3759. Min Act: -0.1700
Data Index: 4373411 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3759. Min Range: -6.3759
Max Act: 5.3759. Min Act: -0.1700
Data Index: 2076903 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19