Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.8066. Min Act: -0.1700
Data Index: 7122163 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.4629. Min Act: -0.1700
Data Index: 7381713 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.2441. Min Act: -0.1700
Data Index: 3739013 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.2129. Min Act: -0.1700
Data Index: 775738 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.1816. Min Act: -0.1700
Data Index: 3560263 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.1504. Min Act: -0.1700
Data Index: 8526788 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.0566. Min Act: -0.1700
Data Index: 5454228 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.0566. Min Act: -0.1700
Data Index: 7689431 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.0566. Min Act: -0.1700
Data Index: 3222862 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.0566. Min Act: -0.1700
Data Index: 4936033 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.0566. Min Act: -0.1700
Data Index: 6625232 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.0254. Min Act: -0.1700
Data Index: 301900 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.0254. Min Act: -0.1700
Data Index: 7370152 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8066. Min Range: -7.8066
Max Act: 7.0254. Min Act: -0.1700
Data Index: 2751445 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8066. Min Range: -7.8066
Max Act: 6.9941. Min Act: -0.1700
Data Index: 3135646 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8066. Min Range: -7.8066
Max Act: 6.9629. Min Act: -0.1700
Data Index: 4914879 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8066. Min Range: -7.8066
Max Act: 6.9629. Min Act: -0.1700
Data Index: 623105 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8066. Min Range: -7.8066
Max Act: 6.9629. Min Act: -0.1700
Data Index: 2222796 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8066. Min Range: -7.8066
Max Act: 6.9316. Min Act: -0.1700
Data Index: 7883406 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8066. Min Range: -7.8066
Max Act: 6.9004. Min Act: -0.1700
Data Index: 3718567 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19