Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1053 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.9381. Min Act: -0.1700
Data Index: 7714367 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.8756. Min Act: -0.1700
Data Index: 7860888 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.8756. Min Act: -0.1700
Data Index: 6094998 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.8756. Min Act: -0.1700
Data Index: 3433937 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.8443. Min Act: -0.1700
Data Index: 679269 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.8443. Min Act: -0.1700
Data Index: 3425031 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.8131. Min Act: -0.1700
Data Index: 311155 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.8131. Min Act: -0.1700
Data Index: 6006198 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.7506. Min Act: -0.1700
Data Index: 8606230 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.7506. Min Act: -0.1700
Data Index: 1983779 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.7193. Min Act: -0.1700
Data Index: 770287 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.7193. Min Act: -0.1700
Data Index: 1853806 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.7193. Min Act: -0.1700
Data Index: 3854723 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.6881. Min Act: -0.1700
Data Index: 634475 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.6568. Min Act: -0.1700
Data Index: 4206385 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.6881. Min Act: -0.1700
Data Index: 7120855 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.6568. Min Act: -0.1700
Data Index: 3110496 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.6568. Min Act: -0.1700
Data Index: 2922215 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.6568. Min Act: -0.1700
Data Index: 7741767 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9381. Min Range: -5.9381
Max Act: 5.6568. Min Act: -0.1700
Data Index: 5278053 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19