Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5853 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0899. Min Range: -7.0899
Max Act: 7.0899. Min Act: -0.1700
Data Index: 822633 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.9961. Min Act: -0.1700
Data Index: 6501930 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.9336. Min Act: -0.1700
Data Index: 6886578 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.8399. Min Act: -0.1700
Data Index: 6406302 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.8086. Min Act: -0.1700
Data Index: 1853061 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.8086. Min Act: -0.1700
Data Index: 594113 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.7149. Min Act: -0.1700
Data Index: 8294175 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.7461. Min Act: -0.1700
Data Index: 428904 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.6836. Min Act: -0.1700
Data Index: 6007055 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.6524. Min Act: -0.1700
Data Index: 3719232 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.6524. Min Act: -0.1700
Data Index: 8468668 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.6211. Min Act: -0.1700
Data Index: 5029308 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.5899. Min Act: -0.1700
Data Index: 3541828 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.5899. Min Act: -0.1700
Data Index: 4752143 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.5899. Min Act: -0.1700
Data Index: 3745676 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.5586. Min Act: -0.1700
Data Index: 7020606 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.5899. Min Act: -0.1700
Data Index: 1844124 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.5586. Min Act: -0.1700
Data Index: 6954296 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.5586. Min Act: -0.1700
Data Index: 7575930 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0899. Min Range: -7.0899
Max Act: 6.5586. Min Act: -0.1700
Data Index: 7283181 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19