Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1473. Min Range: -5.1473
Max Act: 5.1473. Min Act: -0.1700
Data Index: 1596921 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1473. Min Range: -5.1473
Max Act: 5.0848. Min Act: -0.1700
Data Index: 2881178 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1473. Min Range: -5.1473
Max Act: 5.0535. Min Act: -0.1700
Data Index: 8800812 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9910. Min Act: -0.1700
Data Index: 5423608 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9910. Min Act: -0.1700
Data Index: 1945479 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9910. Min Act: -0.1700
Data Index: 5423607 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9910. Min Act: -0.1700
Data Index: 5197568 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9285. Min Act: -0.1700
Data Index: 6620839 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9598. Min Act: -0.1700
Data Index: 1829743 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9598. Min Act: -0.1700
Data Index: 6714917 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9598. Min Act: -0.1700
Data Index: 5423609 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9598. Min Act: -0.1700
Data Index: 5423610 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9598. Min Act: -0.1700
Data Index: 76626 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9285. Min Act: -0.1700
Data Index: 4128777 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9285. Min Act: -0.1700
Data Index: 5423611 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9285. Min Act: -0.1700
Data Index: 3677049 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9285. Min Act: -0.1700
Data Index: 611545 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9285. Min Act: -0.1700
Data Index: 3542261 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9285. Min Act: -0.1700
Data Index: 6714916 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1473. Min Range: -5.1473
Max Act: 4.9285. Min Act: -0.1700
Data Index: 2906654 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19