Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 405 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3417. Min Range: -6.3417
Max Act: 6.3417. Min Act: -0.1700
Data Index: 5988301 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3417. Min Range: -6.3417
Max Act: 6.2167. Min Act: -0.1700
Data Index: 8784083 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3417. Min Range: -6.3417
Max Act: 6.1854. Min Act: -0.1700
Data Index: 7516472 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3417. Min Range: -6.3417
Max Act: 6.1542. Min Act: -0.1700
Data Index: 2395576 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3417. Min Range: -6.3417
Max Act: 6.0917. Min Act: -0.1700
Data Index: 8231293 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3417. Min Range: -6.3417
Max Act: 6.0917. Min Act: -0.1700
Data Index: 6161615 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3417. Min Range: -6.3417
Max Act: 6.0604. Min Act: -0.1700
Data Index: 7078409 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3417. Min Range: -6.3417
Max Act: 6.0604. Min Act: -0.1700
Data Index: 5861881 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9979. Min Act: -0.1700
Data Index: 1445425 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9979. Min Act: -0.1700
Data Index: 5178671 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9979. Min Act: -0.1700
Data Index: 1340813 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9667. Min Act: -0.1700
Data Index: 5284617 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9354. Min Act: -0.1700
Data Index: 2924950 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9354. Min Act: -0.1700
Data Index: 7064566 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9667. Min Act: -0.1700
Data Index: 1358128 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9042. Min Act: -0.1700
Data Index: 3425889 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9042. Min Act: -0.1700
Data Index: 7490816 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9042. Min Act: -0.1700
Data Index: 4579857 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.8729. Min Act: -0.1700
Data Index: 8475964 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3417. Min Range: -6.3417
Max Act: 5.9042. Min Act: -0.1700
Data Index: 2194543 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19