Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5590 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.1738. Min Act: -0.1700
Data Index: 8058563 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.1423. Min Act: -0.1700
Data Index: 632885 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.1423. Min Act: -0.1700
Data Index: 1660721 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.1108. Min Act: -0.1700
Data Index: 8069798 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.1265. Min Act: -0.1700
Data Index: 5213737 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.1108. Min Act: -0.1700
Data Index: 7673890 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0950. Min Act: -0.1700
Data Index: 8585786 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0950. Min Act: -0.1700
Data Index: 4336527 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0950. Min Act: -0.1700
Data Index: 5559734 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0950. Min Act: -0.1700
Data Index: 777951 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 8458981 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 8704281 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 4419920 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0635. Min Act: -0.1700
Data Index: 3959615 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0635. Min Act: -0.1700
Data Index: 98581 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0635. Min Act: -0.1700
Data Index: 1999011 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0635. Min Act: -0.1700
Data Index: 1930777 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0635. Min Act: -0.1700
Data Index: 7545894 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0635. Min Act: -0.1700
Data Index: 7330319 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0635. Min Act: -0.1700
Data Index: 4524109 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19