Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 652 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.5048. Min Act: -0.1696
Data Index: 621251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.4735. Min Act: -0.1700
Data Index: 7104780 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.4423. Min Act: -0.1700
Data Index: 860500 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.4110. Min Act: -0.1700
Data Index: 4671814 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.4110. Min Act: -0.1700
Data Index: 7622087 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.4110. Min Act: -0.1700
Data Index: 3951252 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3798. Min Act: -0.1700
Data Index: 2832863 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3485. Min Act: -0.1700
Data Index: 8466646 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3798. Min Act: -0.1700
Data Index: 4868525 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.4110. Min Act: -0.1700
Data Index: 4671812 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3798. Min Act: -0.1700
Data Index: 3759526 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3798. Min Act: -0.1700
Data Index: 3301218 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3485. Min Act: -0.1700
Data Index: 512324 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3485. Min Act: -0.1700
Data Index: 3210299 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3485. Min Act: -0.1700
Data Index: 2126686 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3485. Min Act: -0.1700
Data Index: 7231052 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3485. Min Act: -0.1685
Data Index: 5634176 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3485. Min Act: -0.1700
Data Index: 8065289 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3485. Min Act: -0.1700
Data Index: 4604021 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5048. Min Range: -5.5048
Max Act: 5.3485. Min Act: -0.1700
Data Index: 1790448 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19