Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3855 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0809. Min Act: -0.1700
Data Index: 2690349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0809. Min Act: -0.1700
Data Index: 429800 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0496. Min Act: -0.1700
Data Index: 2358108 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0496. Min Act: -0.1700
Data Index: 4767881 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0496. Min Act: -0.1700
Data Index: 4821636 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0496. Min Act: -0.1700
Data Index: 2249152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 315003 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 4012102 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 8488629 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 8133430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 7020021 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 6916325 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 6161797 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 2821072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9871. Min Act: -0.1700
Data Index: 742626 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 4352801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 4188112 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9871. Min Act: -0.1700
Data Index: 3829231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9871. Min Act: -0.1700
Data Index: 3892369 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9871. Min Act: -0.1700
Data Index: 4004781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19