Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0160. Min Range: -6.0160
Max Act: 6.0160. Min Act: -0.1700
Data Index: 4725770 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.7660. Min Act: -0.1700
Data Index: 4168933 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.7660. Min Act: -0.1700
Data Index: 5129871 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.7348. Min Act: -0.1700
Data Index: 4414026 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.6723. Min Act: -0.1700
Data Index: 3386100 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.6410. Min Act: -0.1700
Data Index: 8323346 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.6723. Min Act: -0.1700
Data Index: 704275 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.6098. Min Act: -0.1700
Data Index: 7638731 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.6098. Min Act: -0.1700
Data Index: 3044559 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.6098. Min Act: -0.1700
Data Index: 2837965 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.6098. Min Act: -0.1700
Data Index: 1523368 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.6410. Min Act: -0.1700
Data Index: 2113182 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.5785. Min Act: -0.1700
Data Index: 8133425 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.5785. Min Act: -0.1700
Data Index: 155978 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.5785. Min Act: -0.1700
Data Index: 1043879 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.6098. Min Act: -0.1700
Data Index: 2329079 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.5473. Min Act: -0.1700
Data Index: 6664293 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.5473. Min Act: -0.1700
Data Index: 7569802 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.5160. Min Act: -0.1700
Data Index: 4812277 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.5160. Min Act: -0.1700
Data Index: 678338 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19