Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3676 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5648. Min Range: -6.5648
Max Act: 6.5648. Min Act: -0.1700
Data Index: 472708 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5648. Min Range: -6.5648
Max Act: 6.3773. Min Act: -0.1700
Data Index: 5773812 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5648. Min Range: -6.5648
Max Act: 6.1898. Min Act: -0.1700
Data Index: 4531640 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5648. Min Range: -6.5648
Max Act: 6.0648. Min Act: -0.1700
Data Index: 4581963 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5648. Min Range: -6.5648
Max Act: 6.0336. Min Act: -0.1700
Data Index: 5265891 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.9711. Min Act: -0.1700
Data Index: 4772308 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.9711. Min Act: -0.1700
Data Index: 2306862 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.9398. Min Act: -0.1700
Data Index: 4772309 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.8773. Min Act: -0.1700
Data Index: 4772307 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.8773. Min Act: -0.1700
Data Index: 637563 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.8461. Min Act: -0.1700
Data Index: 2481128 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.8461. Min Act: -0.1700
Data Index: 4772310 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.8461. Min Act: -0.1700
Data Index: 6136067 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.7836. Min Act: -0.1700
Data Index: 2774612 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.7836. Min Act: -0.1700
Data Index: 4872724 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.7523. Min Act: -0.1700
Data Index: 3608241 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.7836. Min Act: -0.1700
Data Index: 1477177 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.7836. Min Act: -0.1700
Data Index: 7463472 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.7523. Min Act: -0.1700
Data Index: 2090612 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5648. Min Range: -6.5648
Max Act: 5.7523. Min Act: -0.1700
Data Index: 6563655 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19