Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3780. Min Range: -9.3780
Max Act: 9.3780. Min Act: -0.1700
Data Index: 4399290 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3780. Min Range: -9.3780
Max Act: 9.3155. Min Act: -0.1700
Data Index: 8520675 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.9405. Min Act: -0.1700
Data Index: 2888229 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.9405. Min Act: -0.1700
Data Index: 6926348 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.8780. Min Act: -0.1700
Data Index: 4474242 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.9405. Min Act: -0.1700
Data Index: 6568716 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.8780. Min Act: -0.1700
Data Index: 7933195 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.8155. Min Act: -0.1700
Data Index: 7583898 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.8155. Min Act: -0.1700
Data Index: 8757937 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.7530. Min Act: -0.1700
Data Index: 2939562 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.7530. Min Act: -0.1700
Data Index: 4827514 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.7530. Min Act: -0.1700
Data Index: 8751302 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.6280. Min Act: -0.1700
Data Index: 2472396 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.6280. Min Act: -0.1700
Data Index: 1805149 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.6905. Min Act: -0.1700
Data Index: 5212743 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.5655. Min Act: -0.1700
Data Index: 4185514 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.5655. Min Act: -0.1700
Data Index: 4561361 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.5655. Min Act: -0.1700
Data Index: 1382986 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.5655. Min Act: -0.1700
Data Index: 2881766 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3780. Min Range: -9.3780
Max Act: 8.5655. Min Act: -0.1700
Data Index: 5874021 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19