Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4732 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.6680. Min Act: -0.1700
Data Index: 6024989 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.3867. Min Act: -0.1700
Data Index: 2785165 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.2617. Min Act: -0.1700
Data Index: 5262640 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.1992. Min Act: -0.1700
Data Index: 5415519 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.1992. Min Act: -0.1700
Data Index: 4688011 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.1367. Min Act: -0.1700
Data Index: 6936718 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.1055. Min Act: -0.1700
Data Index: 7352944 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.0742. Min Act: -0.1700
Data Index: 2134413 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.0117. Min Act: -0.1700
Data Index: 3455422 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.0117. Min Act: -0.1700
Data Index: 5849102 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6680. Min Range: -6.6680
Max Act: 6.0117. Min Act: -0.1700
Data Index: 723257 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6680. Min Range: -6.6680
Max Act: 5.9492. Min Act: -0.1700
Data Index: 7515512 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6680. Min Range: -6.6680
Max Act: 5.9805. Min Act: -0.1700
Data Index: 1627805 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6680. Min Range: -6.6680
Max Act: 5.9492. Min Act: -0.1700
Data Index: 4970242 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6680. Min Range: -6.6680
Max Act: 5.9492. Min Act: -0.1700
Data Index: 1285470 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6680. Min Range: -6.6680
Max Act: 5.9492. Min Act: -0.1700
Data Index: 2329308 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6680. Min Range: -6.6680
Max Act: 5.9492. Min Act: -0.1700
Data Index: 6936699 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6680. Min Range: -6.6680
Max Act: 5.8867. Min Act: -0.1700
Data Index: 3457971 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6680. Min Range: -6.6680
Max Act: 5.9180. Min Act: -0.1700
Data Index: 5770430 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6680. Min Range: -6.6680
Max Act: 5.8867. Min Act: -0.1700
Data Index: 3179362 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19