Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 236 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1831. Min Range: -4.1831
Max Act: 4.1831. Min Act: -0.1700
Data Index: 8083011 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1831. Min Range: -4.1831
Max Act: 4.1518. Min Act: -0.1700
Data Index: 4491327 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.9955. Min Act: -0.1700
Data Index: 2548470 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.9955. Min Act: -0.1700
Data Index: 3749050 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.9330. Min Act: -0.1700
Data Index: 5051794 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.9643. Min Act: -0.1700
Data Index: 1793468 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.9330. Min Act: -0.1700
Data Index: 4321 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.9330. Min Act: -0.1700
Data Index: 3221365 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.9017. Min Act: -0.1700
Data Index: 8327560 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.8705. Min Act: -0.1700
Data Index: 4559047 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.8705. Min Act: -0.1700
Data Index: 6773431 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.8079. Min Act: -0.1700
Data Index: 992785 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.8079. Min Act: -0.1700
Data Index: 3732051 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.8079. Min Act: -0.1700
Data Index: 142027 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.7610. Min Act: -0.1700
Data Index: 6125487 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.7610. Min Act: -0.1700
Data Index: 6673222 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.7454. Min Act: -0.1700
Data Index: 4379746 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.7454. Min Act: -0.1700
Data Index: 5647479 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.7297. Min Act: -0.1700
Data Index: 2029320 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1831. Min Range: -4.1831
Max Act: 3.7141. Min Act: -0.1700
Data Index: 5794328 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19