Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5341 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1012. Min Range: -6.1012
Max Act: 6.1012. Min Act: -0.1700
Data Index: 8034475 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1012. Min Range: -6.1012
Max Act: 6.0074. Min Act: -0.1700
Data Index: 4427965 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.9137. Min Act: -0.1700
Data Index: 1530490 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.8512. Min Act: -0.1700
Data Index: 2092526 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.8512. Min Act: -0.1700
Data Index: 3971237 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.8512. Min Act: -0.1700
Data Index: 2232224 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.8824. Min Act: -0.1700
Data Index: 760722 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.7574. Min Act: -0.1700
Data Index: 603926 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.7262. Min Act: -0.1700
Data Index: 2485283 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.7262. Min Act: -0.1700
Data Index: 6475476 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.6949. Min Act: -0.1700
Data Index: 1345972 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.7262. Min Act: -0.1700
Data Index: 8658843 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.6637. Min Act: -0.1700
Data Index: 6701695 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.6324. Min Act: -0.1700
Data Index: 3125495 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.6324. Min Act: -0.1700
Data Index: 3461388 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.6012. Min Act: -0.1700
Data Index: 4570921 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.5387. Min Act: -0.1700
Data Index: 503650 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.5074. Min Act: -0.1700
Data Index: 5025881 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.5074. Min Act: -0.1700
Data Index: 4228962 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1012. Min Range: -6.1012
Max Act: 5.5387. Min Act: -0.1700
Data Index: 4508931 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19