Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.3473. Min Act: -0.1700
Data Index: 2841072 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.3473. Min Act: -0.1700
Data Index: 109246 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.3473. Min Act: -0.1700
Data Index: 8748503 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.1910. Min Act: -0.1700
Data Index: 432273 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.1598. Min Act: -0.1700
Data Index: 4322764 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.1285. Min Act: -0.1700
Data Index: 3814481 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.0973. Min Act: -0.1700
Data Index: 42969 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.0973. Min Act: -0.1700
Data Index: 6018139 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.0973. Min Act: -0.1700
Data Index: 4045031 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.0348. Min Act: -0.1700
Data Index: 2869666 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.0348. Min Act: -0.1700
Data Index: 8316187 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.0035. Min Act: -0.1700
Data Index: 1654407 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3473. Min Range: -6.3473
Max Act: 5.9723. Min Act: -0.1700
Data Index: 661859 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.0035. Min Act: -0.1700
Data Index: 1523633 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3473. Min Range: -6.3473
Max Act: 6.0035. Min Act: -0.1700
Data Index: 5666582 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3473. Min Range: -6.3473
Max Act: 5.9723. Min Act: -0.1700
Data Index: 8359160 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3473. Min Range: -6.3473
Max Act: 5.9723. Min Act: -0.1700
Data Index: 4230897 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3473. Min Range: -6.3473
Max Act: 5.9723. Min Act: -0.1700
Data Index: 783178 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3473. Min Range: -6.3473
Max Act: 5.9723. Min Act: -0.1700
Data Index: 7230977 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3473. Min Range: -6.3473
Max Act: 5.9410. Min Act: -0.1700
Data Index: 4257828 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19