Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4573 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0704. Min Range: -4.0704
Max Act: 4.0704. Min Act: -0.1700
Data Index: 3292378 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0704. Min Range: -4.0704
Max Act: 4.0079. Min Act: -0.1700
Data Index: 2035624 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.9766. Min Act: -0.1700
Data Index: 1891507 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.9454. Min Act: -0.1700
Data Index: 3059776 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.9766. Min Act: -0.1700
Data Index: 4547172 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.9766. Min Act: -0.1700
Data Index: 632594 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.9766. Min Act: -0.1700
Data Index: 6326818 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.9454. Min Act: -0.1700
Data Index: 498654 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.9454. Min Act: -0.1700
Data Index: 636588 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.9141. Min Act: -0.1700
Data Index: 4868457 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.9141. Min Act: -0.1700
Data Index: 5835084 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.9141. Min Act: -0.1700
Data Index: 336029 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.8828. Min Act: -0.1700
Data Index: 4353551 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.8828. Min Act: -0.1700
Data Index: 637018 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.8828. Min Act: -0.1700
Data Index: 4338486 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.8828. Min Act: -0.1700
Data Index: 4060617 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.8828. Min Act: -0.1700
Data Index: 5771111 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.8516. Min Act: -0.1700
Data Index: 5137195 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.8516. Min Act: -0.1700
Data Index: 5606665 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.8516. Min Act: -0.1700
Data Index: 1193403 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19