Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3725 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.8069. Min Act: -0.1700
Data Index: 7508545 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.7131. Min Act: -0.1700
Data Index: 3224170 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.6819. Min Act: -0.1700
Data Index: 2648364 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.6194. Min Act: -0.1700
Data Index: 8561389 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.6194. Min Act: -0.1700
Data Index: 3486798 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.6194. Min Act: -0.1700
Data Index: 3224601 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.6194. Min Act: -0.1700
Data Index: 6840734 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5881. Min Act: -0.1700
Data Index: 5870770 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5881. Min Act: -0.1700
Data Index: 2268337 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5881. Min Act: -0.1700
Data Index: 965350 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5881. Min Act: -0.1700
Data Index: 264285 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5881. Min Act: -0.1700
Data Index: 6924321 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5881. Min Act: -0.1700
Data Index: 6299065 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5881. Min Act: -0.1700
Data Index: 2693563 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5881. Min Act: -0.1700
Data Index: 1951209 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5569. Min Act: -0.1700
Data Index: 6297688 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5569. Min Act: -0.1700
Data Index: 5982644 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5569. Min Act: -0.1700
Data Index: 5346975 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5569. Min Act: -0.1700
Data Index: 163316 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8069. Min Range: -5.8069
Max Act: 5.5569. Min Act: -0.1700
Data Index: 283176 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19