Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5312. Min Range: -8.5312
Max Act: 8.5312. Min Act: -0.1700
Data Index: 4305846 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5312. Min Range: -8.5312
Max Act: 8.0937. Min Act: -0.1700
Data Index: 6599386 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5312. Min Range: -8.5312
Max Act: 8.0312. Min Act: -0.1700
Data Index: 5773366 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.8437. Min Act: -0.1700
Data Index: 1346231 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.8437. Min Act: -0.1700
Data Index: 5343125 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.8437. Min Act: -0.1700
Data Index: 6396240 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.7812. Min Act: -0.1700
Data Index: 3040903 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.7812. Min Act: -0.1700
Data Index: 6934660 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.7812. Min Act: -0.1700
Data Index: 1473996 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.7500. Min Act: -0.1700
Data Index: 3116138 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.7187. Min Act: -0.1700
Data Index: 4825167 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.6875. Min Act: -0.1700
Data Index: 4694251 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.6562. Min Act: -0.1700
Data Index: 3150438 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.6250. Min Act: -0.1700
Data Index: 7591329 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.6250. Min Act: -0.1700
Data Index: 8520347 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.6250. Min Act: -0.1700
Data Index: 4546812 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.6250. Min Act: -0.1700
Data Index: 3572287 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.6250. Min Act: -0.1700
Data Index: 2273731 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.5937. Min Act: -0.1700
Data Index: 4408216 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5312. Min Range: -8.5312
Max Act: 7.5937. Min Act: -0.1700
Data Index: 397778 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19