Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8269. Min Range: -10.8269
Max Act: 10.8269. Min Act: -0.1700
Data Index: 2339496 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8269. Min Range: -10.8269
Max Act: 10.7019. Min Act: -0.1700
Data Index: 3227840 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8269. Min Range: -10.8269
Max Act: 10.2644. Min Act: -0.1700
Data Index: 3227841 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8269. Min Range: -10.8269
Max Act: 10.2644. Min Act: -0.1700
Data Index: 2339497 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8269. Min Range: -10.8269
Max Act: 9.8269. Min Act: -0.1700
Data Index: 5394523 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8269. Min Range: -10.8269
Max Act: 9.1394. Min Act: -0.1700
Data Index: 6971940 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8269. Min Range: -10.8269
Max Act: 9.0769. Min Act: -0.1700
Data Index: 7024938 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.9519. Min Act: -0.1700
Data Index: 7768850 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.8269. Min Act: -0.1700
Data Index: 6950304 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.8894. Min Act: -0.1700
Data Index: 2886480 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.8269. Min Act: -0.1700
Data Index: 453708 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.6394. Min Act: -0.1700
Data Index: 1158957 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.6394. Min Act: -0.1700
Data Index: 7768849 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.6394. Min Act: -0.1700
Data Index: 5862834 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.6394. Min Act: -0.1700
Data Index: 7076438 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.5769. Min Act: -0.1700
Data Index: 1248083 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.5769. Min Act: -0.1700
Data Index: 821182 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.5769. Min Act: -0.1700
Data Index: 3471783 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.5769. Min Act: -0.1700
Data Index: 2768558 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8269. Min Range: -10.8269
Max Act: 8.5769. Min Act: -0.1700
Data Index: 1615822 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19