Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.8971. Min Act: -0.1700
Data Index: 4292606 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.7409. Min Act: -0.1700
Data Index: 4292607 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.4909. Min Act: -0.1700
Data Index: 1979057 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.3971. Min Act: -0.1700
Data Index: 7274675 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.3659. Min Act: -0.1700
Data Index: 1236487 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.3659. Min Act: -0.1700
Data Index: 3728241 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.3659. Min Act: -0.1700
Data Index: 3311551 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.2721. Min Act: -0.1700
Data Index: 4644944 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.2096. Min Act: -0.1700
Data Index: 4998420 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.2096. Min Act: -0.1700
Data Index: 3888648 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.1784. Min Act: -0.1700
Data Index: 5405155 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.1784. Min Act: -0.1700
Data Index: 5778559 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.1471. Min Act: -0.1700
Data Index: 4369705 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.1471. Min Act: -0.1700
Data Index: 4520540 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.1471. Min Act: -0.1700
Data Index: 2128617 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.0846. Min Act: -0.1700
Data Index: 1701368 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.0846. Min Act: -0.1700
Data Index: 3175448 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.0846. Min Act: -0.1700
Data Index: 5568201 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.0846. Min Act: -0.1700
Data Index: 4921734 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8971. Min Range: -6.8971
Max Act: 6.0846. Min Act: -0.1700
Data Index: 6843315 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19