Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4423 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1125. Min Range: -7.1125
Max Act: 7.1125. Min Act: -0.1700
Data Index: 3395191 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1125. Min Range: -7.1125
Max Act: 7.1125. Min Act: -0.1700
Data Index: 3015050 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1125. Min Range: -7.1125
Max Act: 7.0812. Min Act: -0.1700
Data Index: 1992960 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1125. Min Range: -7.1125
Max Act: 7.0500. Min Act: -0.1700
Data Index: 1717218 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1125. Min Range: -7.1125
Max Act: 7.0187. Min Act: -0.1700
Data Index: 5520642 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.9875. Min Act: -0.1700
Data Index: 421668 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.9250. Min Act: -0.1700
Data Index: 1116963 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.8937. Min Act: -0.1700
Data Index: 7991690 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.8312. Min Act: -0.1700
Data Index: 2056842 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.8000. Min Act: -0.1700
Data Index: 4235862 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.7687. Min Act: -0.1700
Data Index: 2029942 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.7687. Min Act: -0.1700
Data Index: 1576461 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.7375. Min Act: -0.1700
Data Index: 8685071 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.7062. Min Act: -0.1700
Data Index: 2444809 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.6750. Min Act: -0.1700
Data Index: 683237 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.6437. Min Act: -0.1700
Data Index: 4917738 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.6125. Min Act: -0.1700
Data Index: 1882802 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.5812. Min Act: -0.1700
Data Index: 8685069 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.5812. Min Act: -0.1700
Data Index: 3721312 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1125. Min Range: -7.1125
Max Act: 6.5812. Min Act: -0.1700
Data Index: 608430 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19