Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2819 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.6789. Min Act: -0.1700
Data Index: 1390137 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.4602. Min Act: -0.1700
Data Index: 117045 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.3977. Min Act: -0.1700
Data Index: 8714005 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.3977. Min Act: -0.1700
Data Index: 8736978 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.3352. Min Act: -0.1700
Data Index: 1796767 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.3352. Min Act: -0.1700
Data Index: 4325973 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.3352. Min Act: -0.1700
Data Index: 2350122 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.3039. Min Act: -0.1700
Data Index: 4416555 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.2727. Min Act: -0.1700
Data Index: 6900619 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.2102. Min Act: -0.1700
Data Index: 8804325 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.1789. Min Act: -0.1700
Data Index: 6136787 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.1789. Min Act: -0.1700
Data Index: 2192393 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.1477. Min Act: -0.1700
Data Index: 8339485 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.1477. Min Act: -0.1700
Data Index: 4785691 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.1164. Min Act: -0.1700
Data Index: 4900521 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.1164. Min Act: -0.1700
Data Index: 7278225 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.0852. Min Act: -0.1700
Data Index: 5722904 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.0852. Min Act: -0.1700
Data Index: 5438636 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.0539. Min Act: -0.1700
Data Index: 1895590 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6789. Min Range: -7.6789
Max Act: 7.0227. Min Act: -0.1700
Data Index: 4733625 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19