Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5796 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2562. Min Range: -5.2562
Max Act: 5.2562. Min Act: -0.1700
Data Index: 323251 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2562. Min Range: -5.2562
Max Act: 5.1000. Min Act: -0.1700
Data Index: 4268460 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.9437. Min Act: -0.1700
Data Index: 791086 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.8500. Min Act: -0.1700
Data Index: 7881023 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.8187. Min Act: -0.1700
Data Index: 5032857 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.7250. Min Act: -0.1700
Data Index: 7110717 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.7250. Min Act: -0.1700
Data Index: 2713518 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.7250. Min Act: -0.1700
Data Index: 8104181 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6937. Min Act: -0.1700
Data Index: 4421862 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6625. Min Act: -0.1700
Data Index: 5414568 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6937. Min Act: -0.1700
Data Index: 2088192 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6625. Min Act: -0.1700
Data Index: 5375325 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6312. Min Act: -0.1700
Data Index: 7493158 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6312. Min Act: -0.1700
Data Index: 6285572 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6000. Min Act: -0.1700
Data Index: 1230465 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6000. Min Act: -0.1700
Data Index: 47727 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6000. Min Act: -0.1700
Data Index: 3435653 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6312. Min Act: -0.1700
Data Index: 1242924 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6000. Min Act: -0.1700
Data Index: 6770897 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2562. Min Range: -5.2562
Max Act: 4.6000. Min Act: -0.1700
Data Index: 4577162 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19