Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0071. Min Range: -7.0071
Max Act: 7.0071. Min Act: -0.1700
Data Index: 4902986 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.7259. Min Act: -0.1700
Data Index: 4624001 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.6634. Min Act: -0.1700
Data Index: 2671093 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.6009. Min Act: -0.1700
Data Index: 6209424 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.5384. Min Act: -0.1700
Data Index: 2570906 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.5071. Min Act: -0.1700
Data Index: 4835321 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.4446. Min Act: -0.1700
Data Index: 8118250 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.4446. Min Act: -0.1700
Data Index: 4190128 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.3509. Min Act: -0.1700
Data Index: 2161327 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.3509. Min Act: -0.1700
Data Index: 353012 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.3196. Min Act: -0.1700
Data Index: 2664415 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.2884. Min Act: -0.1700
Data Index: 5159447 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.2571. Min Act: -0.1700
Data Index: 734727 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.2571. Min Act: -0.1700
Data Index: 2666060 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.2571. Min Act: -0.1700
Data Index: 6435321 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.2259. Min Act: -0.1700
Data Index: 6562497 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.2571. Min Act: -0.1700
Data Index: 7567587 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.1946. Min Act: -0.1700
Data Index: 3535510 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.1634. Min Act: -0.1700
Data Index: 7027706 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0071. Min Range: -7.0071
Max Act: 6.1946. Min Act: -0.1700
Data Index: 757573 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19