Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 10.1858. Min Range: -10.1858
Max Act: 10.1858. Min Act: -0.1700
Data Index: 3992901 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1858. Min Range: -10.1858
Max Act: 10.1233. Min Act: -0.1700
Data Index: 1916186 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.9358. Min Act: -0.1700
Data Index: 6238572 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.8733. Min Act: -0.1700
Data Index: 5072856 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.8108. Min Act: -0.1700
Data Index: 7587513 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.8733. Min Act: -0.1700
Data Index: 8236293 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.7483. Min Act: -0.1700
Data Index: 1810984 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.8108. Min Act: -0.1700
Data Index: 1503544 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.7483. Min Act: -0.1700
Data Index: 8642806 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.6233. Min Act: -0.1700
Data Index: 8710036 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.6858. Min Act: -0.1700
Data Index: 6983564 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.6858. Min Act: -0.1700
Data Index: 1734108 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.5608. Min Act: -0.1700
Data Index: 3682654 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.6233. Min Act: -0.1700
Data Index: 8703809 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.5608. Min Act: -0.1700
Data Index: 1319479 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.6233. Min Act: -0.1700
Data Index: 1962716 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.4983. Min Act: -0.1700
Data Index: 6622495 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.4358. Min Act: -0.1700
Data Index: 7159809 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.4983. Min Act: -0.1700
Data Index: 2224263 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1858. Min Range: -10.1858
Max Act: 9.3733. Min Act: -0.1700
Data Index: 1448659 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19