Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5074 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0775. Min Range: -2.0775
Max Act: 2.0775. Min Act: -0.1700
Data Index: 3759820 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0775. Min Range: -2.0775
Max Act: 2.0439. Min Act: -0.1700
Data Index: 1460204 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0775. Min Range: -2.0775
Max Act: 2.0271. Min Act: -0.1700
Data Index: 6688135 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0775. Min Range: -2.0775
Max Act: 2.0017. Min Act: -0.1700
Data Index: 1709471 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0775. Min Range: -2.0775
Max Act: 2.0017. Min Act: -0.1700
Data Index: 5157772 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9848. Min Act: -0.1700
Data Index: 8156354 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9933. Min Act: -0.1700
Data Index: 2521815 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9848. Min Act: -0.1700
Data Index: 2056877 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9848. Min Act: -0.1700
Data Index: 5583051 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9848. Min Act: -0.1700
Data Index: 8007596 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9848. Min Act: -0.1700
Data Index: 3713148 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9679. Min Act: -0.1700
Data Index: 7097808 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9679. Min Act: -0.1700
Data Index: 812854 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9679. Min Act: -0.1700
Data Index: 8735916 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9594. Min Act: -0.1700
Data Index: 5673064 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9509. Min Act: -0.1700
Data Index: 1709472 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9424. Min Act: -0.1700
Data Index: 3181790 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9509. Min Act: -0.1700
Data Index: 4045173 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9509. Min Act: -0.1700
Data Index: 7309385 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0775. Min Range: -2.0775
Max Act: 1.9424. Min Act: -0.1700
Data Index: 3982127 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19