Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1024 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.4012. Min Act: -0.1700
Data Index: 1764771 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.2865. Min Act: -0.1700
Data Index: 6781183 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.2204. Min Act: -0.1700
Data Index: 6698634 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.2204. Min Act: -0.1700
Data Index: 6201469 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.1706. Min Act: -0.1700
Data Index: 1764770 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.1373. Min Act: -0.1700
Data Index: 7580731 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.1373. Min Act: -0.1700
Data Index: 4742136 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.1038. Min Act: -0.1700
Data Index: 3944936 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.1206. Min Act: -0.1700
Data Index: 8143087 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.1038. Min Act: -0.1700
Data Index: 6972293 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.0871. Min Act: -0.1700
Data Index: 960322 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.0871. Min Act: -0.1700
Data Index: 7196205 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.0703. Min Act: -0.1700
Data Index: 3930194 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.0871. Min Act: -0.1700
Data Index: 1200720 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.0703. Min Act: -0.1700
Data Index: 3281931 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.0871. Min Act: -0.1700
Data Index: 1662881 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.0535. Min Act: -0.1700
Data Index: 6782843 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.0535. Min Act: -0.1700
Data Index: 4482914 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.0535. Min Act: -0.1700
Data Index: 941363 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4012. Min Range: -2.4012
Max Act: 2.0703. Min Act: -0.1700
Data Index: 6903565 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19