Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1722. Min Range: -8.1722
Max Act: 8.1722. Min Act: -0.1700
Data Index: 3257659 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1722. Min Range: -8.1722
Max Act: 8.1722. Min Act: -0.1700
Data Index: 8075848 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1722. Min Range: -8.1722
Max Act: 8.0472. Min Act: -0.1700
Data Index: 1240000 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1722. Min Range: -8.1722
Max Act: 8.0159. Min Act: -0.1700
Data Index: 7218324 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.9847. Min Act: -0.1700
Data Index: 3425263 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.9222. Min Act: -0.1700
Data Index: 700702 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.8909. Min Act: -0.1700
Data Index: 3482393 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.8284. Min Act: -0.1700
Data Index: 1775314 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.7659. Min Act: -0.1700
Data Index: 2544008 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.7659. Min Act: -0.1700
Data Index: 3196901 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.7347. Min Act: -0.1700
Data Index: 6717336 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.7659. Min Act: -0.1700
Data Index: 7957528 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.7347. Min Act: -0.1700
Data Index: 6226827 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.7034. Min Act: -0.1700
Data Index: 4926119 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.6722. Min Act: -0.1700
Data Index: 7191790 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.6722. Min Act: -0.1700
Data Index: 3370424 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.6409. Min Act: -0.1700
Data Index: 6534584 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.6097. Min Act: -0.1700
Data Index: 2364244 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.6722. Min Act: -0.1700
Data Index: 6633218 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1722. Min Range: -8.1722
Max Act: 7.6409. Min Act: -0.1700
Data Index: 5812576 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19