Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1840 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.1638. Min Act: -0.1700
Data Index: 5276734 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.1638. Min Act: -0.1700
Data Index: 986238 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.1325. Min Act: -0.1700
Data Index: 5512054 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.1325. Min Act: -0.1700
Data Index: 8818493 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.1013. Min Act: -0.1700
Data Index: 8042854 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.1013. Min Act: -0.1700
Data Index: 990942 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.1013. Min Act: -0.1700
Data Index: 4518492 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.1013. Min Act: -0.1700
Data Index: 5316642 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.1013. Min Act: -0.1700
Data Index: 1126614 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.0388. Min Act: -0.1700
Data Index: 8622601 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.0388. Min Act: -0.1700
Data Index: 757963 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.0388. Min Act: -0.1700
Data Index: 765067 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.0700. Min Act: -0.1698
Data Index: 6066544 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.0388. Min Act: -0.1700
Data Index: 710114 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.0388. Min Act: -0.1700
Data Index: 5902334 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.0075. Min Act: -0.1700
Data Index: 5844680 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.0075. Min Act: -0.1700
Data Index: 3565357 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.0075. Min Act: -0.1700
Data Index: 5009523 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1638. Min Range: -6.1638
Max Act: 6.0075. Min Act: -0.1700
Data Index: 2796482 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1638. Min Range: -6.1638
Max Act: 5.9763. Min Act: -0.1698
Data Index: 7482784 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19