Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.8854. Min Act: -0.1700
Data Index: 5456984 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.8229. Min Act: -0.1700
Data Index: 5456983 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.7292. Min Act: -0.1700
Data Index: 8320839 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6979. Min Act: -0.1700
Data Index: 4122414 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6979. Min Act: -0.1700
Data Index: 6961098 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6667. Min Act: -0.1700
Data Index: 104196 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6667. Min Act: -0.1700
Data Index: 104197 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6354. Min Act: -0.1700
Data Index: 4041845 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6042. Min Act: -0.1700
Data Index: 1180280 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6042. Min Act: -0.1700
Data Index: 7685300 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6042. Min Act: -0.1700
Data Index: 1347870 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6042. Min Act: -0.1700
Data Index: 6480790 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6042. Min Act: -0.1700
Data Index: 3131332 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6042. Min Act: -0.1700
Data Index: 4279304 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.5417. Min Act: -0.1700
Data Index: 1536193 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.5729. Min Act: -0.1700
Data Index: 144838 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.5729. Min Act: -0.1700
Data Index: 2619062 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.5729. Min Act: -0.1700
Data Index: 4176836 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.6042. Min Act: -0.1700
Data Index: 2992345 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8854. Min Range: -6.8854
Max Act: 6.5417. Min Act: -0.1700
Data Index: 6961104 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19