Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4511 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3101. Min Range: -5.3101
Max Act: 5.3101. Min Act: -0.1700
Data Index: 375753 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.9351. Min Act: -0.1700
Data Index: 5975514 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.9664. Min Act: -0.1700
Data Index: 4600341 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.9664. Min Act: -0.1700
Data Index: 812053 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.9039. Min Act: -0.1700
Data Index: 3159384 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.8414. Min Act: -0.1700
Data Index: 7310124 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.7476. Min Act: -0.1700
Data Index: 203632 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.7476. Min Act: -0.1700
Data Index: 1039698 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.7476. Min Act: -0.1700
Data Index: 8333280 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.7476. Min Act: -0.1700
Data Index: 6091740 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.6851. Min Act: -0.1700
Data Index: 741340 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.6851. Min Act: -0.1700
Data Index: 8334302 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.6851. Min Act: -0.1700
Data Index: 7147651 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.6539. Min Act: -0.1700
Data Index: 7681105 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.6539. Min Act: -0.1700
Data Index: 6676182 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.6539. Min Act: -0.1700
Data Index: 5416524 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.6539. Min Act: -0.1700
Data Index: 2759953 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.5914. Min Act: -0.1700
Data Index: 865757 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.6226. Min Act: -0.1700
Data Index: 1533331 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3101. Min Range: -5.3101
Max Act: 4.5914. Min Act: -0.1700
Data Index: 1775806 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19