Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1382 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.8157. Min Act: -0.1700
Data Index: 1518146 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.8157. Min Act: -0.1700
Data Index: 7633962 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.5657. Min Act: -0.1700
Data Index: 2326088 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.5969. Min Act: -0.1700
Data Index: 3530346 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.5032. Min Act: -0.1700
Data Index: 8087496 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.5032. Min Act: -0.1700
Data Index: 610506 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.5032. Min Act: -0.1700
Data Index: 3572202 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4719. Min Act: -0.1700
Data Index: 3959437 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4719. Min Act: -0.1700
Data Index: 4366718 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4719. Min Act: -0.1700
Data Index: 5659785 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4719. Min Act: -0.1700
Data Index: 5330261 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4407. Min Act: -0.1700
Data Index: 5664161 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4407. Min Act: -0.1700
Data Index: 5637665 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4407. Min Act: -0.1700
Data Index: 4407423 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4094. Min Act: -0.1700
Data Index: 7281827 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4407. Min Act: -0.1700
Data Index: 172645 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4407. Min Act: -0.1700
Data Index: 2219530 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.3782. Min Act: -0.1700
Data Index: 7594867 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.4094. Min Act: -0.1700
Data Index: 3672624 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8157. Min Range: -5.8157
Max Act: 5.3782. Min Act: -0.1700
Data Index: 1254109 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19