Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3011 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.1219. Min Act: -0.1700
Data Index: 3479016 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0746. Min Act: -0.1700
Data Index: 3218544 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0588. Min Act: -0.1700
Data Index: 7568267 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0431. Min Act: -0.1700
Data Index: 8081985 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0273. Min Act: -0.1700
Data Index: 6018950 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0273. Min Act: -0.1700
Data Index: 8419877 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0273. Min Act: -0.1700
Data Index: 5939676 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0273. Min Act: -0.1700
Data Index: 5903613 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0273. Min Act: -0.1700
Data Index: 3380629 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0115. Min Act: -0.1700
Data Index: 3218543 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0115. Min Act: -0.1700
Data Index: 6018951 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1219. Min Range: -3.1219
Max Act: 3.0115. Min Act: -0.1700
Data Index: 6482728 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1219. Min Range: -3.1219
Max Act: 2.9957. Min Act: -0.1700
Data Index: 446753 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1219. Min Range: -3.1219
Max Act: 2.9957. Min Act: -0.1700
Data Index: 530592 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1219. Min Range: -3.1219
Max Act: 2.9957. Min Act: -0.1700
Data Index: 7364424 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1219. Min Range: -3.1219
Max Act: 2.9957. Min Act: -0.1700
Data Index: 7308944 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1219. Min Range: -3.1219
Max Act: 2.9957. Min Act: -0.1700
Data Index: 7250570 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1219. Min Range: -3.1219
Max Act: 2.9957. Min Act: -0.1700
Data Index: 3299686 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1219. Min Range: -3.1219
Max Act: 2.9799. Min Act: -0.1700
Data Index: 4344251 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1219. Min Range: -3.1219
Max Act: 2.9799. Min Act: -0.1700
Data Index: 1194766 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19