Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4262 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2173. Min Range: -6.2173
Max Act: 6.2173. Min Act: -0.1700
Data Index: 4623060 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2173. Min Range: -6.2173
Max Act: 6.1860. Min Act: -0.1700
Data Index: 3596475 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.9673. Min Act: -0.1700
Data Index: 3623044 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.9048. Min Act: -0.1700
Data Index: 3724992 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.9048. Min Act: -0.1700
Data Index: 7776003 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.9360. Min Act: -0.1700
Data Index: 4014856 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.9048. Min Act: -0.1700
Data Index: 4399294 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.9048. Min Act: -0.1700
Data Index: 7507983 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.8423. Min Act: -0.1700
Data Index: 4614954 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.8735. Min Act: -0.1700
Data Index: 392078 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.8735. Min Act: -0.1700
Data Index: 2394032 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.8423. Min Act: -0.1700
Data Index: 4064869 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.8423. Min Act: -0.1700
Data Index: 4655643 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.8423. Min Act: -0.1700
Data Index: 6453111 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.8110. Min Act: -0.1700
Data Index: 692087 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.8110. Min Act: -0.1700
Data Index: 3655956 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.7173. Min Act: -0.1700
Data Index: 5175585 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.7485. Min Act: -0.1700
Data Index: 5554653 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.7173. Min Act: -0.1700
Data Index: 275154 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2173. Min Range: -6.2173
Max Act: 5.7173. Min Act: -0.1700
Data Index: 1826445 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19