Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1858 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4848. Min Act: -0.1700
Data Index: 1841982 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4848. Min Act: -0.1700
Data Index: 8505431 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4848. Min Act: -0.1700
Data Index: 5560979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4535. Min Act: -0.1700
Data Index: 6044462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4848. Min Act: -0.1700
Data Index: 3217770 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4535. Min Act: -0.1700
Data Index: 3450417 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4535. Min Act: -0.1700
Data Index: 4930135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4535. Min Act: -0.1700
Data Index: 2501980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4535. Min Act: -0.1700
Data Index: 6354063 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4535. Min Act: -0.1700
Data Index: 3980325 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4223. Min Act: -0.1700
Data Index: 1893176 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.3910. Min Act: -0.1700
Data Index: 8707869 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4223. Min Act: -0.1700
Data Index: 3980328 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.4223. Min Act: -0.1700
Data Index: 3946054 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.3910. Min Act: -0.1700
Data Index: 8458881 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.3910. Min Act: -0.1700
Data Index: 6547016 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.3910. Min Act: -0.1700
Data Index: 5423245 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.3910. Min Act: -0.1700
Data Index: 4778116 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.3598. Min Act: -0.1700
Data Index: 6132697 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4848. Min Range: -4.4848
Max Act: 4.3598. Min Act: -0.1700
Data Index: 1987205 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19