Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5925 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.4941. Min Act: -0.1700
Data Index: 35843 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.3379. Min Act: -0.1700
Data Index: 4690334 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.3379. Min Act: -0.1700
Data Index: 70129 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.3066. Min Act: -0.1700
Data Index: 5395424 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.2754. Min Act: -0.1700
Data Index: 2084930 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.2129. Min Act: -0.1700
Data Index: 70135 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.1816. Min Act: -0.1700
Data Index: 5099936 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.1816. Min Act: -0.1700
Data Index: 70138 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.1816. Min Act: -0.1700
Data Index: 70139 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.1816. Min Act: -0.1700
Data Index: 197805 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.1504. Min Act: -0.1700
Data Index: 6513410 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.1504. Min Act: -0.1700
Data Index: 4786141 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.1504. Min Act: -0.1700
Data Index: 70132 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.1191. Min Act: -0.1700
Data Index: 70134 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.1191. Min Act: -0.1700
Data Index: 8324884 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.0879. Min Act: -0.1700
Data Index: 710040 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.0879. Min Act: -0.1700
Data Index: 3460473 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.0879. Min Act: -0.1700
Data Index: 3890596 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.0879. Min Act: -0.1700
Data Index: 7113330 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4941. Min Range: -5.4941
Max Act: 5.1191. Min Act: -0.1700
Data Index: 7270549 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19