Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.5492. Min Act: -0.1700
Data Index: 8765286 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.5007. Min Act: -0.1700
Data Index: 6993502 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.5007. Min Act: -0.1700
Data Index: 8826850 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.4845. Min Act: -0.1700
Data Index: 7400406 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.4520. Min Act: -0.1700
Data Index: 7092476 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.4357. Min Act: -0.1700
Data Index: 3065301 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.4520. Min Act: -0.1700
Data Index: 1540158 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.4194. Min Act: -0.1700
Data Index: 8557618 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3868. Min Act: -0.1700
Data Index: 7247457 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3868. Min Act: -0.1700
Data Index: 6608862 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3868. Min Act: -0.1700
Data Index: 4893498 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3868. Min Act: -0.1700
Data Index: 3171794 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3868. Min Act: -0.1700
Data Index: 5169448 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3705. Min Act: -0.1700
Data Index: 8424628 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3868. Min Act: -0.1700
Data Index: 6704810 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3868. Min Act: -0.1700
Data Index: 7494460 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3705. Min Act: -0.1700
Data Index: 1336593 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3541. Min Act: -0.1700
Data Index: 3339189 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3705. Min Act: -0.1700
Data Index: 7250876 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5492. Min Range: -2.5492
Max Act: 2.3868. Min Act: -0.1700
Data Index: 6808760 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19