Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4114 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7929. Min Act: -0.1700
Data Index: 7453742 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7239. Min Act: -0.1700
Data Index: 5937485 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6718. Min Act: -0.1700
Data Index: 263076 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6545. Min Act: -0.1700
Data Index: 4161675 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6545. Min Act: -0.1700
Data Index: 606943 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6545. Min Act: -0.1700
Data Index: 3122737 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6196. Min Act: -0.1700
Data Index: 6350051 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6196. Min Act: -0.1700
Data Index: 467958 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6196. Min Act: -0.1700
Data Index: 6318681 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6022. Min Act: -0.1699
Data Index: 7319535 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6022. Min Act: -0.1700
Data Index: 7386914 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.5847. Min Act: -0.1700
Data Index: 8556434 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6022. Min Act: -0.1700
Data Index: 1596596 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.5847. Min Act: -0.1700
Data Index: 6545336 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.5672. Min Act: -0.1700
Data Index: 5115714 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.5672. Min Act: -0.1700
Data Index: 2716058 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.5672. Min Act: -0.1700
Data Index: 6289623 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.5672. Min Act: -0.1700
Data Index: 1998623 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.5497. Min Act: -0.1700
Data Index: 6637258 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.5672. Min Act: -0.1700
Data Index: 3786264 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19