Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6343 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.6563. Min Act: -0.1700
Data Index: 2559413 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.6251. Min Act: -0.1700
Data Index: 270323 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.5001. Min Act: -0.1700
Data Index: 6084487 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.5001. Min Act: -0.1700
Data Index: 1514214 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.3751. Min Act: -0.1700
Data Index: 7631142 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.3438. Min Act: -0.1700
Data Index: 2012999 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.2813. Min Act: -0.1700
Data Index: 7563095 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.2813. Min Act: -0.1700
Data Index: 5451019 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.2501. Min Act: -0.1700
Data Index: 5452107 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.1563. Min Act: -0.1700
Data Index: 4211336 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.1563. Min Act: -0.1700
Data Index: 485748 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.1251. Min Act: -0.1700
Data Index: 5779299 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.0626. Min Act: -0.1700
Data Index: 8638465 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.0938. Min Act: -0.1700
Data Index: 1956111 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.0626. Min Act: -0.1700
Data Index: 2926694 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.0626. Min Act: -0.1700
Data Index: 2301733 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.0313. Min Act: -0.1700
Data Index: 4940046 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.0313. Min Act: -0.1700
Data Index: 529354 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6563. Min Range: -6.6563
Max Act: 6.0001. Min Act: -0.1700
Data Index: 6057766 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6563. Min Range: -6.6563
Max Act: 5.9688. Min Act: -0.1700
Data Index: 3640750 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19