Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 525 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 8733018 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 7121250 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 4822935 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 6923526 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 558927 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 1000829 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 1840391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 5120047 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 7214728 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 230626 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.5129. Min Act: -0.1700
Data Index: 1688119 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.4805. Min Act: -0.1700
Data Index: 4932711 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3992. Min Act: -0.1700
Data Index: 1680004 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3829. Min Act: -0.1700
Data Index: 1113374 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3665. Min Act: -0.1700
Data Index: 1411486 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3665. Min Act: -0.1700
Data Index: 8109587 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3501. Min Act: -0.1700
Data Index: 5293063 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3501. Min Act: -0.1700
Data Index: 8710876 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3337. Min Act: -0.1700
Data Index: 1322433 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5129. Min Range: -2.5129
Max Act: 2.3337. Min Act: -0.1700
Data Index: 5809550 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19