Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3857. Min Range: -7.3857
Max Act: 7.3857. Min Act: -0.1700
Data Index: 7601544 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3857. Min Range: -7.3857
Max Act: 7.2920. Min Act: -0.1700
Data Index: 2800322 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3857. Min Range: -7.3857
Max Act: 7.2607. Min Act: -0.1700
Data Index: 5793764 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3857. Min Range: -7.3857
Max Act: 7.1357. Min Act: -0.1700
Data Index: 2827353 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3857. Min Range: -7.3857
Max Act: 7.1045. Min Act: -0.1700
Data Index: 3888881 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.9795. Min Act: -0.1700
Data Index: 4979064 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3857. Min Range: -7.3857
Max Act: 7.0420. Min Act: -0.1700
Data Index: 1069864 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.9795. Min Act: -0.1700
Data Index: 5297454 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.9482. Min Act: -0.1700
Data Index: 285467 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.9482. Min Act: -0.1700
Data Index: 7392334 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.9170. Min Act: -0.1700
Data Index: 2165387 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.9170. Min Act: -0.1700
Data Index: 219576 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.8857. Min Act: -0.1700
Data Index: 4585784 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.8545. Min Act: -0.1700
Data Index: 8419388 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.8545. Min Act: -0.1700
Data Index: 4582375 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.8232. Min Act: -0.1700
Data Index: 4176731 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.8545. Min Act: -0.1700
Data Index: 1859699 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.8232. Min Act: -0.1700
Data Index: 4714147 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.8232. Min Act: -0.1700
Data Index: 433717 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3857. Min Range: -7.3857
Max Act: 6.7920. Min Act: -0.1700
Data Index: 1640097 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19